diff --git "a/profile_trace/iteration_195584/rank0_trace.json" "b/profile_trace/iteration_195584/rank0_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_195584/rank0_trace.json" @@ -0,0 +1,83427 @@ + +{ + "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": 0, "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": "026F26A8C3D847DEB0B1DB53F1703252", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359415589.940, "dur": 152.679, + "args": { + "External id": 4725249,"Record function id": 0, "Sequence number": 47018994, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359415622.704, "dur": 109.887, + "args": { + "External id": 4725250,"Sequence number": 47018994, "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": 1336753, "tid": 1381210, "ts": 1712359415622.704, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1381210, + "ts": 1712359415632.559, "dur": 97.854, + "args": { + "External id": 4725251,"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": 1336753, "tid": 1381210, + "ts": 1712359415754.447, "dur": 333.695, + "args": { + "External id": 4725252,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359415827.503, "dur": 112.300, + "args": { + "External id": 4725253,"Record function id": 0, "Ev Idx": 4 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.27", "pid": 1336753, "tid": 1381210, + "ts": 1712359415864.407, "dur": 63.559, + "args": { + "External id": 4725254,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359415944.826, "dur": 2.249, + "args": { + "External id": 4725255,"Sequence number": 47018993, "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": 1336753, "tid": 1381210, "ts": 1712359415944.826, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359415953.195, "dur": 127.377, + "args": { + "External id": 4725256,"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": 1336753, "tid": 1381210, + "ts": 1712359415971.528, "dur": 108.047, + "args": { + "External id": 4725257,"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": 1336753, "tid": 1381210, + "ts": 1712359415982.266, "dur": 39.092, + "args": { + "External id": 4725258,"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": 1336753, "tid": 1381210, + "ts": 1712359416100.641, "dur": 36365.811, + "args": { + "External id": 4725259,"Record function id": 0, "Sequence number": 47018991, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359416102.791, "dur": 36349.594, + "args": { + "External id": 4725260,"Sequence number": 47018991, "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": 1336753, "tid": 1381210, "ts": 1712359416102.791, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359416159.299, "dur": 4.613, + "args": { + "External id": 4725261,"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": 1336753, "tid": 1381210, + "ts": 1712359416169.887, "dur": 36154.755, + "args": { + "External id": 4725262,"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": 1336753, "tid": 1381210, + "ts": 1712359416172.495, "dur": 36151.589, + "args": { + "External id": 4725263,"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": 1336753, "tid": 1381210, + "ts": 1712359416178.176, "dur": 11.111, + "args": { + "External id": 4725264,"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": 1336753, "tid": 1381210, + "ts": 1712359416191.817, "dur": 36130.832, + "args": { + "External id": 4725265,"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": 1336753, "tid": 1381210, + "ts": 1712359452330.242, "dur": 0.603, + "args": { + "External id": 4725266,"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": 1336753, "tid": 1381210, + "ts": 1712359452333.497, "dur": 3.631, + "args": { + "External id": 4725267,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 18 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452335.553, "dur": 1.264, + "args": { + "External id": 4725268,"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": 1336753, "tid": 1381210, + "ts": 1712359452344.489, "dur": 34.442, + "args": { + "External id": 4725269,"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": 1336753, "tid": 1381210, + "ts": 1712359452388.629, "dur": 52.716, + "args": { + "External id": 4725270,"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": 1336753, "tid": 1381210, + "ts": 1712359452390.775, "dur": 50.366, + "args": { + "External id": 4725271,"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": 1336753, "tid": 1381210, + "ts": 1712359452393.035, "dur": 47.791, + "args": { + "External id": 4725272,"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": 1336753, "tid": 1381210, + "ts": 1712359452478.105, "dur": 22.240, + "args": { + "External id": 4725273,"Record function id": 0, "Sequence number": 47018990, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452479.858, "dur": 16.231, + "args": { + "External id": 4725274,"Sequence number": 47018990, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 25 + } + }, + { + "ph": "f", "id": 4, "pid": 1336753, "tid": 1381210, "ts": 1712359452479.858, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359452485.183, "dur": 10.686, + "args": { + "External id": 4725275,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 26 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359452488.990, "dur": 6.713, + "args": { + "External id": 4725276,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 27 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452504.452, "dur": 109.192, + "args": { + "External id": 4725277,"Record function id": 0, "Sequence number": 47018989, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452505.898, "dur": 96.265, + "args": { + "External id": 4725278,"Sequence number": 47018989, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 29 + } + }, + { + "ph": "f", "id": 5, "pid": 1336753, "tid": 1381210, "ts": 1712359452505.898, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359452509.954, "dur": 91.740, + "args": { + "External id": 4725279,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 30 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359452515.920, "dur": 39.181, + "args": { + "External id": 4725280,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 31 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359452520.465, "dur": 6.712, + "args": { + "External id": 4725281,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 32 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452529.086, "dur": 25.701, + "args": { + "External id": 4725282,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 33 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452534.657, "dur": 19.657, + "args": { + "External id": 4725283,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 34 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359452558.319, "dur": 4.747, + "args": { + "External id": 4725284,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 35 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359452561.228, "dur": 1.499, + "args": { + "External id": 4725285,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[8388608, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 36 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452564.518, "dur": 36.394, + "args": { + "External id": 4725286,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 37 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452618.475, "dur": 65.906, + "args": { + "External id": 4725287,"Record function id": 0, "Sequence number": 47018988, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452619.718, "dur": 60.353, + "args": { + "External id": 4725288,"Sequence number": 47018988, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 39 + } + }, + { + "ph": "f", "id": 6, "pid": 1336753, "tid": 1381210, "ts": 1712359452619.718, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359452623.066, "dur": 56.707, + "args": { + "External id": 4725289,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "2", "3"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 40 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359452627.771, "dur": 20.384, + "args": { + "External id": 4725290,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 41 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359452628.770, "dur": 3.825, + "args": { + "External id": 4725291,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 42 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452633.374, "dur": 14.503, + "args": { + "External id": 4725292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 43 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452636.671, "dur": 10.858, + "args": { + "External id": 4725293,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 44 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1712359452652.522, "dur": 6.334, + "args": { + "External id": 4725294,"Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 45 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359452656.807, "dur": 1.156, + "args": { + "External id": 4725295,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "6144"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 46 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452659.757, "dur": 19.360, + "args": { + "External id": 4725296,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 47 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452688.366, "dur": 113.263, + "args": { + "External id": 4725297,"Record function id": 0, "Sequence number": 47018987, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452689.473, "dur": 106.802, + "args": { + "External id": 4725298,"Sequence number": 47018987, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 49 + } + }, + { + "ph": "f", "id": 7, "pid": 1336753, "tid": 1381210, "ts": 1712359452689.473, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359452694.014, "dur": 101.957, + "args": { + "External id": 4725299,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 50 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359452697.920, "dur": 14.419, + "args": { + "External id": 4725300,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 51 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359452698.493, "dur": 2.445, + "args": { + "External id": 4725301,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 52 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452701.462, "dur": 10.627, + "args": { + "External id": 4725302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 53 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452702.283, "dur": 9.511, + "args": { + "External id": 4725303,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 54 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359452715.704, "dur": 3.871, + "args": { + "External id": 4725304,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 55 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359452717.071, "dur": 2.351, + "args": { + "External id": 4725305,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 56 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452720.636, "dur": 74.535, + "args": { + "External id": 4725306,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 57 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452807.967, "dur": 91.855, + "args": { + "External id": 4725307,"Record function id": 0, "Sequence number": 47018986, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452809.119, "dur": 87.352, + "args": { + "External id": 4725308,"Sequence number": 47018986, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 59 + } + }, + { + "ph": "f", "id": 8, "pid": 1336753, "tid": 1381210, "ts": 1712359452809.119, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359452810.587, "dur": 85.567, + "args": { + "External id": 4725309,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 60 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359452813.938, "dur": 15.520, + "args": { + "External id": 4725310,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 61 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359452814.925, "dur": 2.712, + "args": { + "External id": 4725311,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 62 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452818.264, "dur": 10.961, + "args": { + "External id": 4725312,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 63 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452818.845, "dur": 10.089, + "args": { + "External id": 4725313,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 64 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359452832.219, "dur": 3.801, + "args": { + "External id": 4725314,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 65 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359452835.420, "dur": 0.467, + "args": { + "External id": 4725315,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 66 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359452836.608, "dur": 58.934, + "args": { + "External id": 4725316,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 67 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452903.940, "dur": 38.564, + "args": { + "External id": 4725317,"Record function id": 0, "Sequence number": 47018985, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359452905.398, "dur": 1.073, + "args": { + "External id": 4725318,"Sequence number": 47018985, "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": 1336753, "tid": 1381210, "ts": 1712359452905.398, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359452909.320, "dur": 28.647, + "args": { + "External id": 4725319,"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": 1336753, "tid": 1381210, + "ts": 1712359452911.624, "dur": 25.917, + "args": { + "External id": 4725320,"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": 1336753, "tid": 1381210, + "ts": 1712359452920.674, "dur": 0.558, + "args": { + "External id": 4725321,"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": 1336753, "tid": 1381210, + "ts": 1712359452947.351, "dur": 2285.129, + "args": { + "External id": 4725322,"Record function id": 0, "Sequence number": 47018983, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359452948.454, "dur": 2248.423, + "args": { + "External id": 4725323,"Sequence number": 47018983, "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": 1336753, "tid": 1381210, "ts": 1712359452948.454, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359453017.481, "dur": 3.132, + "args": { + "External id": 4725324,"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": 1336753, "tid": 1381210, + "ts": 1712359453023.417, "dur": 2087.693, + "args": { + "External id": 4725325,"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": 1336753, "tid": 1381210, + "ts": 1712359453025.039, "dur": 2085.762, + "args": { + "External id": 4725326,"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": 1336753, "tid": 1381210, + "ts": 1712359453027.491, "dur": 6.298, + "args": { + "External id": 4725327,"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": 1336753, "tid": 1381210, + "ts": 1712359453036.496, "dur": 2073.311, + "args": { + "External id": 4725328,"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": 1336753, "tid": 1381210, + "ts": 1712359455114.291, "dur": 0.323, + "args": { + "External id": 4725329,"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": 1336753, "tid": 1381210, + "ts": 1712359455116.188, "dur": 2.227, + "args": { + "External id": 4725330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 81 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455117.608, "dur": 0.689, + "args": { + "External id": 4725331,"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": 1336753, "tid": 1381210, + "ts": 1712359455122.441, "dur": 20.790, + "args": { + "External id": 4725332,"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": 1336753, "tid": 1381210, + "ts": 1712359455148.537, "dur": 40.379, + "args": { + "External id": 4725333,"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": 1336753, "tid": 1381210, + "ts": 1712359455149.642, "dur": 39.072, + "args": { + "External id": 4725334,"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": 1336753, "tid": 1381210, + "ts": 1712359455150.679, "dur": 37.681, + "args": { + "External id": 4725335,"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": 1336753, "tid": 1381210, + "ts": 1712359455207.353, "dur": 20.745, + "args": { + "External id": 4725336,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 87 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455239.821, "dur": 16.025, + "args": { + "External id": 4725337,"Record function id": 0, "Sequence number": 47018982, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455243.065, "dur": 9.921, + "args": { + "External id": 4725338,"Sequence number": 47018982, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 89 + } + }, + { + "ph": "f", "id": 11, "pid": 1336753, "tid": 1381210, "ts": 1712359455243.065, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359455247.380, "dur": 5.432, + "args": { + "External id": 4725339,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 90 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359455248.952, "dur": 3.735, + "args": { + "External id": 4725340,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 91 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455259.161, "dur": 68.203, + "args": { + "External id": 4725341,"Record function id": 0, "Sequence number": 47018981, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455260.000, "dur": 60.527, + "args": { + "External id": 4725342,"Sequence number": 47018981, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 93 + } + }, + { + "ph": "f", "id": 12, "pid": 1336753, "tid": 1381210, "ts": 1712359455260.000, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359455261.639, "dur": 58.525, + "args": { + "External id": 4725343,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 94 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359455265.565, "dur": 22.034, + "args": { + "External id": 4725344,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 95 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359455266.919, "dur": 4.616, + "args": { + "External id": 4725345,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 96 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455272.253, "dur": 15.085, + "args": { + "External id": 4725346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 97 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455273.364, "dur": 13.554, + "args": { + "External id": 4725347,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 98 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359455288.941, "dur": 2.629, + "args": { + "External id": 4725348,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 99 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359455290.580, "dur": 0.749, + "args": { + "External id": 4725349,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[8388608, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455294.376, "dur": 24.924, + "args": { + "External id": 4725350,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455331.060, "dur": 53.312, + "args": { + "External id": 4725351,"Record function id": 0, "Sequence number": 47018980, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455332.069, "dur": 48.573, + "args": { + "External id": 4725352,"Sequence number": 47018980, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 103 + } + }, + { + "ph": "f", "id": 13, "pid": 1336753, "tid": 1381210, "ts": 1712359455332.069, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359455336.991, "dur": 43.430, + "args": { + "External id": 4725353,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "2", "2"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359455338.544, "dur": 18.405, + "args": { + "External id": 4725354,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359455339.108, "dur": 2.443, + "args": { + "External id": 4725355,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455341.992, "dur": 14.704, + "args": { + "External id": 4725356,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455342.668, "dur": 13.623, + "args": { + "External id": 4725357,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1712359455358.002, "dur": 7.734, + "args": { + "External id": 4725358,"Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359455364.371, "dur": 0.802, + "args": { + "External id": 4725359,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455366.460, "dur": 13.480, + "args": { + "External id": 4725360,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455388.087, "dur": 89.746, + "args": { + "External id": 4725361,"Record function id": 0, "Sequence number": 47018979, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455388.943, "dur": 85.058, + "args": { + "External id": 4725362,"Sequence number": 47018979, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 113 + } + }, + { + "ph": "f", "id": 14, "pid": 1336753, "tid": 1381210, "ts": 1712359455388.943, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359455390.411, "dur": 83.213, + "args": { + "External id": 4725363,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359455391.166, "dur": 14.171, + "args": { + "External id": 4725364,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359455392.117, "dur": 2.045, + "args": { + "External id": 4725365,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455394.604, "dur": 10.458, + "args": { + "External id": 4725366,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455395.228, "dur": 9.530, + "args": { + "External id": 4725367,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359455406.178, "dur": 4.609, + "args": { + "External id": 4725368,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359455410.071, "dur": 0.593, + "args": { + "External id": 4725369,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455411.617, "dur": 61.085, + "args": { + "External id": 4725370,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455484.341, "dur": 91.179, + "args": { + "External id": 4725371,"Record function id": 0, "Sequence number": 47018978, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455485.434, "dur": 71.627, + "args": { + "External id": 4725372,"Sequence number": 47018978, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 123 + } + }, + { + "ph": "f", "id": 15, "pid": 1336753, "tid": 1381210, "ts": 1712359455485.434, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359455489.490, "dur": 67.261, + "args": { + "External id": 4725373,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359455490.435, "dur": 14.855, + "args": { + "External id": 4725374,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359455491.179, "dur": 1.648, + "args": { + "External id": 4725375,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455493.327, "dur": 11.713, + "args": { + "External id": 4725376,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455494.293, "dur": 10.418, + "args": { + "External id": 4725377,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359455506.275, "dur": 1.706, + "args": { + "External id": 4725378,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359455507.161, "dur": 0.713, + "args": { + "External id": 4725379,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455508.580, "dur": 47.563, + "args": { + "External id": 4725380,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359455561.089, "dur": 13.191, + "args": { + "External id": 4725381,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455581.571, "dur": 34.305, + "args": { + "External id": 4725382,"Record function id": 0, "Sequence number": 47018977, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359455582.685, "dur": 0.868, + "args": { + "External id": 4725383,"Sequence number": 47018977, "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": 1336753, "tid": 1381210, "ts": 1712359455582.685, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359455586.513, "dur": 25.422, + "args": { + "External id": 4725384,"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": 1336753, "tid": 1381210, + "ts": 1712359455588.412, "dur": 23.077, + "args": { + "External id": 4725385,"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": 1336753, "tid": 1381210, + "ts": 1712359455596.343, "dur": 0.515, + "args": { + "External id": 4725386,"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": 1336753, "tid": 1381210, + "ts": 1712359455620.188, "dur": 3106.502, + "args": { + "External id": 4725387,"Record function id": 0, "Sequence number": 47018975, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359455623.812, "dur": 3078.737, + "args": { + "External id": 4725388,"Sequence number": 47018975, "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": 1336753, "tid": 1381210, "ts": 1712359455623.812, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359455651.926, "dur": 2.236, + "args": { + "External id": 4725389,"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": 1336753, "tid": 1381210, + "ts": 1712359455656.064, "dur": 2962.331, + "args": { + "External id": 4725390,"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": 1336753, "tid": 1381210, + "ts": 1712359455657.372, "dur": 2960.705, + "args": { + "External id": 4725391,"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": 1336753, "tid": 1381210, + "ts": 1712359455659.382, "dur": 4.694, + "args": { + "External id": 4725392,"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": 1336753, "tid": 1381210, + "ts": 1712359455664.898, "dur": 2952.136, + "args": { + "External id": 4725393,"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": 1336753, "tid": 1381210, + "ts": 1712359458621.374, "dur": 0.277, + "args": { + "External id": 4725394,"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": 1336753, "tid": 1381210, + "ts": 1712359458622.733, "dur": 4.222, + "args": { + "External id": 4725395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458626.039, "dur": 0.776, + "args": { + "External id": 4725396,"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": 1336753, "tid": 1381210, + "ts": 1712359458630.644, "dur": 20.061, + "args": { + "External id": 4725397,"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": 1336753, "tid": 1381210, + "ts": 1712359458657.287, "dur": 37.967, + "args": { + "External id": 4725398,"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": 1336753, "tid": 1381210, + "ts": 1712359458658.064, "dur": 37.010, + "args": { + "External id": 4725399,"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": 1336753, "tid": 1381210, + "ts": 1712359458658.967, "dur": 35.869, + "args": { + "External id": 4725400,"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": 1336753, "tid": 1381210, + "ts": 1712359458709.501, "dur": 13.106, + "args": { + "External id": 4725401,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458736.235, "dur": 11.160, + "args": { + "External id": 4725402,"Record function id": 0, "Sequence number": 47018974, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458737.539, "dur": 6.469, + "args": { + "External id": 4725403,"Sequence number": 47018974, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 154 + } + }, + { + "ph": "f", "id": 18, "pid": 1336753, "tid": 1381210, "ts": 1712359458737.539, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359458739.622, "dur": 4.186, + "args": { + "External id": 4725404,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359458740.749, "dur": 2.912, + "args": { + "External id": 4725405,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458750.718, "dur": 63.102, + "args": { + "External id": 4725406,"Record function id": 0, "Sequence number": 47018973, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458753.730, "dur": 54.460, + "args": { + "External id": 4725407,"Sequence number": 47018973, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 158 + } + }, + { + "ph": "f", "id": 19, "pid": 1336753, "tid": 1381210, "ts": 1712359458753.730, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359458756.931, "dur": 50.929, + "args": { + "External id": 4725408,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359458759.179, "dur": 18.555, + "args": { + "External id": 4725409,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359458760.169, "dur": 2.356, + "args": { + "External id": 4725410,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458763.120, "dur": 14.367, + "args": { + "External id": 4725411,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458764.611, "dur": 12.450, + "args": { + "External id": 4725412,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359458778.932, "dur": 4.751, + "args": { + "External id": 4725413,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359458782.630, "dur": 0.856, + "args": { + "External id": 4725414,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[8388608, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458784.336, "dur": 22.861, + "args": { + "External id": 4725415,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458817.866, "dur": 50.917, + "args": { + "External id": 4725416,"Record function id": 0, "Sequence number": 47018972, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458818.935, "dur": 46.283, + "args": { + "External id": 4725417,"Sequence number": 47018972, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 168 + } + }, + { + "ph": "f", "id": 20, "pid": 1336753, "tid": 1381210, "ts": 1712359458818.935, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359458820.689, "dur": 44.273, + "args": { + "External id": 4725418,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "2", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359458824.098, "dur": 18.297, + "args": { + "External id": 4725419,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359458824.776, "dur": 2.326, + "args": { + "External id": 4725420,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458827.685, "dur": 14.452, + "args": { + "External id": 4725421,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458828.369, "dur": 13.436, + "args": { + "External id": 4725422,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1712359458843.388, "dur": 7.692, + "args": { + "External id": 4725423,"Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359458848.167, "dur": 2.375, + "args": { + "External id": 4725424,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458851.543, "dur": 13.031, + "args": { + "External id": 4725425,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458872.278, "dur": 89.785, + "args": { + "External id": 4725426,"Record function id": 0, "Sequence number": 47018971, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458873.385, "dur": 84.919, + "args": { + "External id": 4725427,"Sequence number": 47018971, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 178 + } + }, + { + "ph": "f", "id": 21, "pid": 1336753, "tid": 1381210, "ts": 1712359458873.385, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359458875.020, "dur": 82.924, + "args": { + "External id": 4725428,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359458875.763, "dur": 19.634, + "args": { + "External id": 4725429,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359458878.623, "dur": 1.894, + "args": { + "External id": 4725430,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458881.119, "dur": 14.026, + "args": { + "External id": 4725431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458881.897, "dur": 12.867, + "args": { + "External id": 4725432,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359458896.294, "dur": 3.847, + "args": { + "External id": 4725433,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359458899.561, "dur": 0.408, + "args": { + "External id": 4725434,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458900.562, "dur": 56.501, + "args": { + "External id": 4725435,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458966.018, "dur": 131.457, + "args": { + "External id": 4725436,"Record function id": 0, "Sequence number": 47018970, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359458966.868, "dur": 111.068, + "args": { + "External id": 4725437,"Sequence number": 47018970, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 188 + } + }, + { + "ph": "f", "id": 22, "pid": 1336753, "tid": 1381210, "ts": 1712359458966.868, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359458971.135, "dur": 106.431, + "args": { + "External id": 4725438,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359458972.017, "dur": 42.942, + "args": { + "External id": 4725439,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359458974.599, "dur": 1.679, + "args": { + "External id": 4725440,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458976.761, "dur": 37.901, + "args": { + "External id": 4725441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359458977.650, "dur": 36.257, + "args": { + "External id": 4725442,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359459016.526, "dur": 4.386, + "args": { + "External id": 4725443,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359459019.945, "dur": 0.727, + "args": { + "External id": 4725444,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359459021.717, "dur": 54.881, + "args": { + "External id": 4725445,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359459082.619, "dur": 13.529, + "args": { + "External id": 4725446,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359459103.269, "dur": 30.198, + "args": { + "External id": 4725447,"Record function id": 0, "Sequence number": 47018969, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359459104.494, "dur": 0.822, + "args": { + "External id": 4725448,"Sequence number": 47018969, "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": 1336753, "tid": 1381210, "ts": 1712359459104.494, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359459107.264, "dur": 21.363, + "args": { + "External id": 4725449,"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": 1336753, "tid": 1381210, + "ts": 1712359459108.813, "dur": 19.485, + "args": { + "External id": 4725450,"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": 1336753, "tid": 1381210, + "ts": 1712359459113.145, "dur": 0.593, + "args": { + "External id": 4725451,"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": 1336753, "tid": 1381210, + "ts": 1712359459137.884, "dur": 3086.743, + "args": { + "External id": 4725452,"Record function id": 0, "Sequence number": 47018968, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359459151.075, "dur": 3043.476, + "args": { + "External id": 4725453,"Sequence number": 47018968, "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": 1336753, "tid": 1381210, "ts": 1712359459151.075, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359459178.266, "dur": 2.608, + "args": { + "External id": 4725454,"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": 1336753, "tid": 1381210, + "ts": 1712359459182.742, "dur": 2930.822, + "args": { + "External id": 4725455,"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": 1336753, "tid": 1381210, + "ts": 1712359459183.804, "dur": 2929.375, + "args": { + "External id": 4725456,"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": 1336753, "tid": 1381210, + "ts": 1712359459187.778, "dur": 2.888, + "args": { + "External id": 4725457,"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": 1336753, "tid": 1381210, + "ts": 1712359459191.562, "dur": 2920.724, + "args": { + "External id": 4725458,"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": 1336753, "tid": 1381210, + "ts": 1712359462116.731, "dur": 0.269, + "args": { + "External id": 4725459,"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": 1336753, "tid": 1381210, + "ts": 1712359462118.200, "dur": 1.883, + "args": { + "External id": 4725460,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462119.159, "dur": 0.811, + "args": { + "External id": 4725461,"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": 1336753, "tid": 1381210, + "ts": 1712359462123.283, "dur": 20.788, + "args": { + "External id": 4725462,"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": 1336753, "tid": 1381210, + "ts": 1712359462148.214, "dur": 39.469, + "args": { + "External id": 4725463,"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": 1336753, "tid": 1381210, + "ts": 1712359462149.027, "dur": 38.458, + "args": { + "External id": 4725464,"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": 1336753, "tid": 1381210, + "ts": 1712359462150.087, "dur": 37.148, + "args": { + "External id": 4725465,"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": 1336753, "tid": 1381210, + "ts": 1712359462205.584, "dur": 13.887, + "args": { + "External id": 4725466,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359462235.141, "dur": 12.378, + "args": { + "External id": 4725467,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359462237.763, "dur": 8.015, + "args": { + "External id": 4725468,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359462240.946, "dur": 3.867, + "args": { + "External id": 4725469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359462241.782, "dur": 2.929, + "args": { + "External id": 4725470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462250.926, "dur": 11.470, + "args": { + "External id": 4725471,"Record function id": 0, "Sequence number": 47018967, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462252.049, "dur": 7.664, + "args": { + "External id": 4725472,"Sequence number": 47018967, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 223 + } + }, + { + "ph": "f", "id": 25, "pid": 1336753, "tid": 1381210, "ts": 1712359462252.049, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359462253.979, "dur": 5.553, + "args": { + "External id": 4725473,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359462256.862, "dur": 2.516, + "args": { + "External id": 4725474,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462265.759, "dur": 64.100, + "args": { + "External id": 4725475,"Record function id": 0, "Sequence number": 47018966, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462266.591, "dur": 58.226, + "args": { + "External id": 4725476,"Sequence number": 47018966, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 227 + } + }, + { + "ph": "f", "id": 26, "pid": 1336753, "tid": 1381210, "ts": 1712359462266.591, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359462268.505, "dur": 55.883, + "args": { + "External id": 4725477,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359462272.694, "dur": 20.714, + "args": { + "External id": 4725478,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359462273.759, "dur": 2.651, + "args": { + "External id": 4725479,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462277.091, "dur": 16.052, + "args": { + "External id": 4725480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462278.496, "dur": 14.169, + "args": { + "External id": 4725481,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359462294.759, "dur": 4.308, + "args": { + "External id": 4725482,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359462297.894, "dur": 0.781, + "args": { + "External id": 4725483,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[8388608, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462299.778, "dur": 23.932, + "args": { + "External id": 4725484,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462335.901, "dur": 49.516, + "args": { + "External id": 4725485,"Record function id": 0, "Sequence number": 47018965, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462336.696, "dur": 45.133, + "args": { + "External id": 4725486,"Sequence number": 47018965, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 237 + } + }, + { + "ph": "f", "id": 27, "pid": 1336753, "tid": 1381210, "ts": 1712359462336.696, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359462338.695, "dur": 42.914, + "args": { + "External id": 4725487,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "2", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359462340.294, "dur": 22.662, + "args": { + "External id": 4725488,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359462347.336, "dur": 2.263, + "args": { + "External id": 4725489,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462350.276, "dur": 12.444, + "args": { + "External id": 4725490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462350.980, "dur": 11.361, + "args": { + "External id": 4725491,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1712359462363.921, "dur": 3.531, + "args": { + "External id": 4725492,"Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359462366.394, "dur": 0.686, + "args": { + "External id": 4725493,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462368.173, "dur": 13.038, + "args": { + "External id": 4725494,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462389.061, "dur": 98.006, + "args": { + "External id": 4725495,"Record function id": 0, "Sequence number": 47018964, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462389.965, "dur": 93.462, + "args": { + "External id": 4725496,"Sequence number": 47018964, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 247 + } + }, + { + "ph": "f", "id": 28, "pid": 1336753, "tid": 1381210, "ts": 1712359462389.965, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359462391.550, "dur": 91.501, + "args": { + "External id": 4725497,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359462394.376, "dur": 21.628, + "args": { + "External id": 4725498,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359462395.116, "dur": 2.284, + "args": { + "External id": 4725499,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462400.078, "dur": 15.676, + "args": { + "External id": 4725500,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462400.694, "dur": 14.758, + "args": { + "External id": 4725501,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359462416.923, "dur": 3.832, + "args": { + "External id": 4725502,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359462417.953, "dur": 2.618, + "args": { + "External id": 4725503,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462421.330, "dur": 61.084, + "args": { + "External id": 4725504,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462490.744, "dur": 108.929, + "args": { + "External id": 4725505,"Record function id": 0, "Sequence number": 47018963, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462491.839, "dur": 90.501, + "args": { + "External id": 4725506,"Sequence number": 47018963, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 257 + } + }, + { + "ph": "f", "id": 29, "pid": 1336753, "tid": 1381210, "ts": 1712359462491.839, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359462493.118, "dur": 88.786, + "args": { + "External id": 4725507,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1381210, + "ts": 1712359462494.020, "dur": 36.479, + "args": { + "External id": 4725508,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359462498.300, "dur": 1.667, + "args": { + "External id": 4725509,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462513.733, "dur": 16.423, + "args": { + "External id": 4725510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462518.750, "dur": 11.078, + "args": { + "External id": 4725511,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359462531.296, "dur": 1.444, + "args": { + "External id": 4725512,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359462532.161, "dur": 0.431, + "args": { + "External id": 4725513,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462533.205, "dur": 48.062, + "args": { + "External id": 4725514,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359462586.516, "dur": 11.465, + "args": { + "External id": 4725515,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359462605.077, "dur": 367.985, + "args": { + "External id": 4725516,"Record function id": 0, "Sequence number": 47018962, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359462606.201, "dur": 357.591, + "args": { + "External id": 4725517,"Sequence number": 47018962, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 268 + } + }, + { + "ph": "f", "id": 30, "pid": 1336753, "tid": 1381210, "ts": 1712359462606.201, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462798.023, "dur": 42.053, + "args": { + "External id": 4725518,"kernel_hash": "c2likoimxa3yi6j6dwntng3kzuvmiu64h4ync66w4mrx4v7x6wto", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "262144", "2048", "1", "1986", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/2l/c2likoimxa3yi6j6dwntng3kzuvmiu64h4ync66w4mrx4v7x6wto.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[262144, 2048], [2048], [262144, 2048], [262144, 2048], [132, 2048], [262144], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359462876.575, "dur": 28.834, + "args": { + "External id": 4725519,"kernel_hash": "c2mqya6ilpprpgchmqenn6k5mpg3mienn3ill2mhoh2uq42xagjg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2m/c2mqya6ilpprpgchmqenn6k5mpg3mienn3ill2mhoh2uq42xagjg.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359462922.737, "dur": 17.817, + "args": { + "External id": 4725520,"kernel_hash": "cstbyq2jrfkh2pvulirtdouqrjc47q3sh3z3auux63nbg6d6xj43", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/st/cstbyq2jrfkh2pvulirtdouqrjc47q3sh3z3auux63nbg6d6xj43.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359463016.213, "dur": 15.183, + "args": { + "External id": 4725521,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359463019.399, "dur": 10.911, + "args": { + "External id": 4725522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359463022.456, "dur": 6.576, + "args": { + "External id": 4725523,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359463025.704, "dur": 3.074, + "args": { + "External id": 4725524,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: StackBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463038.797, "dur": 52.758, + "args": { + "External id": 4725525,"Record function id": 0, "Sequence number": 47018961, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463039.688, "dur": 40.175, + "args": { + "External id": 4725526,"Sequence number": 47018961, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 277 + } + }, + { + "ph": "f", "id": 31, "pid": 1336753, "tid": 1381210, "ts": 1712359463039.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1712359463042.066, "dur": 8.483, + "args": { + "External id": 4725527,"Record function id": 0, "Concrete Inputs": ["", "-2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463047.042, "dur": 1.571, + "args": { + "External id": 4725528,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1712359463051.110, "dur": 6.065, + "args": { + "External id": 4725529,"Record function id": 0, "Concrete Inputs": ["", "-2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463055.886, "dur": 0.507, + "args": { + "External id": 4725530,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1712359463057.598, "dur": 2.093, + "args": { + "External id": 4725531,"Record function id": 0, "Concrete Inputs": ["", "-2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463058.444, "dur": 0.486, + "args": { + "External id": 4725532,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1712359463060.057, "dur": 18.697, + "args": { + "External id": 4725533,"Record function id": 0, "Concrete Inputs": ["", "-2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463062.684, "dur": 0.690, + "args": { + "External id": 4725534,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "6144"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463097.325, "dur": 7.932, + "args": { + "External id": 4725535,"Record function id": 0, "Sequence number": 47018960, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463098.417, "dur": 1.635, + "args": { + "External id": 4725536,"Sequence number": 47018960, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 287 + } + }, + { + "ph": "f", "id": 32, "pid": 1336753, "tid": 1381210, "ts": 1712359463098.417, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359463109.733, "dur": 544.718, + "args": { + "External id": 4725537,"Record function id": 0, "Sequence number": 47018959, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359463110.938, "dur": 531.437, + "args": { + "External id": 4725538,"Sequence number": 47018959, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 289 + } + }, + { + "ph": "f", "id": 33, "pid": 1336753, "tid": 1381210, "ts": 1712359463110.938, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359463158.869, "dur": 13.224, + "args": { + "External id": 4725539,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359463167.589, "dur": 4.138, + "args": { + "External id": 4725540,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]", "[8192, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[33554432, 8192, 1], [], []], "Input Dims": [[16, 4096, 2048], [], []], "Ev Idx": 291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359463178.210, "dur": 6.940, + "args": { + "External id": 4725541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359463181.833, "dur": 2.312, + "args": { + "External id": 4725542,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463183.127, "dur": 0.755, + "args": { + "External id": 4725543,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1381210, + "ts": 1712359463192.221, "dur": 144.101, + "args": { + "External id": 4725544,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8192, 1], [1, 5632], []], "Input Dims": [[65536, 2048], [5632, 2048], []], "Ev Idx": 295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359463193.453, "dur": 7.359, + "args": { + "External id": 4725545,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 5632]], "Input Dims": [[5632, 2048]], "Ev Idx": 296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359463193.999, "dur": 5.670, + "args": { + "External id": 4725546,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 5632], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463197.172, "dur": 2.376, + "args": { + "External id": 4725547,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[5632, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 5632], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1381210, + "ts": 1712359463203.160, "dur": 132.416, + "args": { + "External id": 4725548,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359463205.703, "dur": 128.649, + "args": { + "External id": 4725549,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359463344.097, "dur": 5.964, + "args": { + "External id": 4725550,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [23068672, 5632, 1]], "Input Dims": [[65536, 5632], [16, 4096, 5632]], "Ev Idx": 301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359463347.591, "dur": 2.300, + "args": { + "External id": 4725551,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359463390.282, "dur": 4.477, + "args": { + "External id": 4725552,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359463395.662, "dur": 3.400, + "args": { + "External id": 4725553,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359463401.342, "dur": 1.841, + "args": { + "External id": 4725554,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359463441.130, "dur": 2.262, + "args": { + "External id": 4725555,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359463441.993, "dur": 1.244, + "args": { + "External id": 4725556,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 1336753, "tid": 1381210, + "ts": 1712359463475.482, "dur": 145.257, + "args": { + "External id": 4725557,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[8192, 1], [5632, 1]], []], "Input Dims": [[], [[65536, 2048], [65536, 5632]], []], "Ev Idx": 308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1381210, + "ts": 1712359463482.468, "dur": 8.376, + "args": { + "External id": 4725558,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463487.535, "dur": 0.873, + "args": { + "External id": 4725559,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048, 1]", "[8192, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359463492.935, "dur": 8.302, + "args": { + "External id": 4725560,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8192, 1, 1], []], "Input Dims": [[65536, 2048, 1], []], "Ev Idx": 311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463497.770, "dur": 2.696, + "args": { + "External id": 4725561,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 65536]", "[1, 1, 8192]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[65536, 2048, 1], [], [], []], "Ev Idx": 312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1381210, + "ts": 1712359463502.495, "dur": 3.367, + "args": { + "External id": 4725562,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463505.097, "dur": 0.370, + "args": { + "External id": 4725563,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359463506.508, "dur": 3.930, + "args": { + "External id": 4725564,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463509.354, "dur": 0.471, + "args": { + "External id": 4725565,"Record function id": 0, "Concrete Inputs": ["", "[1, 5632, 65536]", "[1, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1, 1], [], [], []], "Input Dims": [[65536, 5632, 1], [], [], []], "Ev Idx": 316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359463514.356, "dur": 4.286, + "args": { + "External id": 4725566,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 8192], []], "Input Dims": [[2048, 1, 65536], []], "Ev Idx": 317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463517.796, "dur": 0.574, + "args": { + "External id": 4725567,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536, 1]", "[1, 8192, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 8192], [], [], []], "Input Dims": [[2048, 1, 65536], [], [], []], "Ev Idx": 318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359463521.523, "dur": 7.146, + "args": { + "External id": 4725568,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 8192, 1], []], "Input Dims": [[2048, 65536, 1], []], "Ev Idx": 319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359463526.619, "dur": 1.877, + "args": { + "External id": 4725569,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]", "[2048, 1, 8192]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 8192, 1], [], []], "Input Dims": [[2048, 65536, 1], [], []], "Ev Idx": 320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359463529.259, "dur": 3.028, + "args": { + "External id": 4725570,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 5632], []], "Input Dims": [[1, 5632, 65536], []], "Ev Idx": 321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463531.639, "dur": 0.332, + "args": { + "External id": 4725571,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 5632], [], [], []], "Input Dims": [[1, 5632, 65536], [], [], []], "Ev Idx": 322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359463532.740, "dur": 2.002, + "args": { + "External id": 4725572,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359463533.222, "dur": 1.417, + "args": { + "External id": 4725573,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359463536.669, "dur": 70.389, + "args": { + "External id": 4725574,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1, 8192], [369098752, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632]], "Ev Idx": 325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359463608.739, "dur": 2.743, + "args": { + "External id": 4725575,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 5632, 1], []], "Input Dims": [[1, 2048, 5632], []], "Ev Idx": 326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359463613.978, "dur": 2.296, + "args": { + "External id": 4725576,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 5632, 1], []], "Input Dims": [[2048, 1, 5632], []], "Ev Idx": 327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463615.005, "dur": 0.590, + "args": { + "External id": 4725577,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632, 1]", "[5632, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 5632, 1], [], [], []], "Input Dims": [[2048, 1, 5632], [], [], []], "Ev Idx": 328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359463618.433, "dur": 0.893, + "args": { + "External id": 4725578,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 5632], []], "Input Dims": [[2048, 5632, 1], []], "Ev Idx": 329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359463664.560, "dur": 8.908, + "args": { + "External id": 4725579,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359463666.365, "dur": 6.289, + "args": { + "External id": 4725580,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359463668.435, "dur": 3.325, + "args": { + "External id": 4725581,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359463669.490, "dur": 2.161, + "args": { + "External id": 4725582,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463677.800, "dur": 9.567, + "args": { + "External id": 4725583,"Record function id": 0, "Sequence number": 47018958, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463678.596, "dur": 5.464, + "args": { + "External id": 4725584,"Sequence number": 47018958, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 335 + } + }, + { + "ph": "f", "id": 34, "pid": 1336753, "tid": 1381210, "ts": 1712359463678.596, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359463682.021, "dur": 1.881, + "args": { + "External id": 4725585,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359463682.708, "dur": 1.043, + "args": { + "External id": 4725586,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463691.270, "dur": 164.030, + "args": { + "External id": 4725587,"Record function id": 0, "Sequence number": 47018957, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463692.530, "dur": 153.453, + "args": { + "External id": 4725588,"Sequence number": 47018957, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 339 + } + }, + { + "ph": "f", "id": 35, "pid": 1336753, "tid": 1381210, "ts": 1712359463692.530, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359463699.320, "dur": 3.734, + "args": { + "External id": 4725589,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359463700.668, "dur": 1.867, + "args": { + "External id": 4725590,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463701.813, "dur": 0.556, + "args": { + "External id": 4725591,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359463704.415, "dur": 53.262, + "args": { + "External id": 4725592,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359463758.781, "dur": 5.216, + "args": { + "External id": 4725593,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359463759.538, "dur": 3.894, + "args": { + "External id": 4725594,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463762.325, "dur": 0.963, + "args": { + "External id": 4725595,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359463765.921, "dur": 4.077, + "args": { + "External id": 4725596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359463766.830, "dur": 2.625, + "args": { + "External id": 4725597,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463768.941, "dur": 0.450, + "args": { + "External id": 4725598,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359463770.690, "dur": 74.584, + "args": { + "External id": 4725599,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463859.599, "dur": 5.889, + "args": { + "External id": 4725600,"Record function id": 0, "Sequence number": 47018956, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463860.434, "dur": 3.815, + "args": { + "External id": 4725601,"Sequence number": 47018956, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 352 + } + }, + { + "ph": "f", "id": 36, "pid": 1336753, "tid": 1381210, "ts": 1712359463860.434, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359463862.177, "dur": 1.932, + "args": { + "External id": 4725602,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359463862.944, "dur": 1.026, + "args": { + "External id": 4725603,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463869.049, "dur": 10.882, + "args": { + "External id": 4725604,"Record function id": 0, "Sequence number": 47018955, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463871.897, "dur": 5.566, + "args": { + "External id": 4725605,"Sequence number": 47018955, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 356 + } + }, + { + "ph": "f", "id": 37, "pid": 1336753, "tid": 1381210, "ts": 1712359463871.897, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359463872.701, "dur": 4.564, + "args": { + "External id": 4725606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359463873.540, "dur": 3.205, + "args": { + "External id": 4725607,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463876.134, "dur": 0.501, + "args": { + "External id": 4725608,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359463883.718, "dur": 5.498, + "args": { + "External id": 4725609,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359463885.013, "dur": 3.700, + "args": { + "External id": 4725610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359463886.134, "dur": 2.230, + "args": { + "External id": 4725611,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359463886.925, "dur": 1.364, + "args": { + "External id": 4725612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463892.657, "dur": 8.636, + "args": { + "External id": 4725613,"Record function id": 0, "Sequence number": 47018954, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463893.484, "dur": 4.398, + "args": { + "External id": 4725614,"Sequence number": 47018954, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 365 + } + }, + { + "ph": "f", "id": 38, "pid": 1336753, "tid": 1381210, "ts": 1712359463893.484, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359463894.659, "dur": 3.087, + "args": { + "External id": 4725615,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359463897.036, "dur": 0.601, + "args": { + "External id": 4725616,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463904.630, "dur": 185.284, + "args": { + "External id": 4725617,"Record function id": 0, "Sequence number": 47018953, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359463905.551, "dur": 156.908, + "args": { + "External id": 4725618,"Sequence number": 47018953, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 369 + } + }, + { + "ph": "f", "id": 39, "pid": 1336753, "tid": 1381210, "ts": 1712359463905.551, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359463907.790, "dur": 2.269, + "args": { + "External id": 4725619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359463908.424, "dur": 1.247, + "args": { + "External id": 4725620,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463909.210, "dur": 0.375, + "args": { + "External id": 4725621,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359463912.329, "dur": 42.846, + "args": { + "External id": 4725622,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359463956.216, "dur": 4.949, + "args": { + "External id": 4725623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359463956.914, "dur": 3.788, + "args": { + "External id": 4725624,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463959.598, "dur": 0.988, + "args": { + "External id": 4725625,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359463962.202, "dur": 7.299, + "args": { + "External id": 4725626,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359463963.267, "dur": 5.804, + "args": { + "External id": 4725627,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359463966.627, "dur": 2.379, + "args": { + "External id": 4725628,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359463970.182, "dur": 90.921, + "args": { + "External id": 4725629,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464099.241, "dur": 37.994, + "args": { + "External id": 4725630,"Record function id": 0, "Sequence number": 47018952, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464100.462, "dur": 6.742, + "args": { + "External id": 4725631,"Sequence number": 47018952, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 382 + } + }, + { + "ph": "f", "id": 40, "pid": 1336753, "tid": 1381210, "ts": 1712359464100.462, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359464102.977, "dur": 4.070, + "args": { + "External id": 4725632,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464105.397, "dur": 1.530, + "args": { + "External id": 4725633,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1381210, + "ts": 1712359464111.252, "dur": 23.278, + "args": { + "External id": 4725634,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464141.058, "dur": 10.712, + "args": { + "External id": 4725635,"Record function id": 0, "Sequence number": 47018951, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464142.217, "dur": 6.951, + "args": { + "External id": 4725636,"Sequence number": 47018951, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 387 + } + }, + { + "ph": "f", "id": 41, "pid": 1336753, "tid": 1381210, "ts": 1712359464142.217, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359464143.303, "dur": 5.634, + "args": { + "External id": 4725637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359464146.245, "dur": 2.137, + "args": { + "External id": 4725638,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464147.589, "dur": 0.702, + "args": { + "External id": 4725639,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359464156.306, "dur": 5.585, + "args": { + "External id": 4725640,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359464157.611, "dur": 3.758, + "args": { + "External id": 4725641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359464158.818, "dur": 2.112, + "args": { + "External id": 4725642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359464159.434, "dur": 1.423, + "args": { + "External id": 4725643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359464166.181, "dur": 476.280, + "args": { + "External id": 4725644,"Record function id": 0, "Sequence number": 47018950, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359464167.334, "dur": 456.128, + "args": { + "External id": 4725645,"Sequence number": 47018950, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 396 + } + }, + { + "ph": "f", "id": 42, "pid": 1336753, "tid": 1381210, "ts": 1712359464167.334, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1712359464198.221, "dur": 33.654, + "args": { + "External id": 4725646,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359464200.197, "dur": 31.476, + "args": { + "External id": 4725647,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359464203.896, "dur": 5.632, + "args": { + "External id": 4725648,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359464206.066, "dur": 2.945, + "args": { + "External id": 4725649,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "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": 1336753, "tid": 1381210, + "ts": 1712359464211.055, "dur": 20.184, + "args": { + "External id": 4725650,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359464244.345, "dur": 3.901, + "args": { + "External id": 4725651,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464246.948, "dur": 1.197, + "args": { + "External id": 4725652,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359464251.610, "dur": 3.652, + "args": { + "External id": 4725653,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464252.273, "dur": 2.894, + "args": { + "External id": 4725654,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359464271.938, "dur": 2.072, + "args": { + "External id": 4725655,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359464289.544, "dur": 3.482, + "args": { + "External id": 4725656,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464516.239, "dur": 2.707, + "args": { + "External id": 4725657,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359464523.554, "dur": 32.780, + "args": { + "External id": 4725658,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464534.182, "dur": 0.755, + "args": { + "External id": 4725659,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359464562.060, "dur": 27.184, + "args": { + "External id": 4725660,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359464563.979, "dur": 25.001, + "args": { + "External id": 4725661,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464567.718, "dur": 4.302, + "args": { + "External id": 4725662,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 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": 1336753, "tid": 1381210, + "ts": 1712359464573.219, "dur": 15.250, + "args": { + "External id": 4725663,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359464596.294, "dur": 2.059, + "args": { + "External id": 4725664,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464597.164, "dur": 1.056, + "args": { + "External id": 4725665,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359464605.060, "dur": 3.829, + "args": { + "External id": 4725666,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464607.715, "dur": 1.074, + "args": { + "External id": 4725667,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359464610.688, "dur": 3.605, + "args": { + "External id": 4725668,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464611.256, "dur": 2.942, + "args": { + "External id": 4725669,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359464652.090, "dur": 6.590, + "args": { + "External id": 4725670,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359464653.653, "dur": 4.327, + "args": { + "External id": 4725671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359464655.008, "dur": 2.085, + "args": { + "External id": 4725672,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359464655.589, "dur": 1.376, + "args": { + "External id": 4725673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464662.162, "dur": 9.585, + "args": { + "External id": 4725674,"Record function id": 0, "Sequence number": 47018949, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464662.917, "dur": 5.666, + "args": { + "External id": 4725675,"Sequence number": 47018949, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 426 + } + }, + { + "ph": "f", "id": 43, "pid": 1336753, "tid": 1381210, "ts": 1712359464662.917, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359464666.667, "dur": 1.724, + "args": { + "External id": 4725676,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464667.298, "dur": 0.962, + "args": { + "External id": 4725677,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464675.366, "dur": 144.012, + "args": { + "External id": 4725678,"Record function id": 0, "Sequence number": 47018948, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464678.413, "dur": 133.992, + "args": { + "External id": 4725679,"Sequence number": 47018948, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 430 + } + }, + { + "ph": "f", "id": 44, "pid": 1336753, "tid": 1381210, "ts": 1712359464678.413, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359464683.251, "dur": 3.606, + "args": { + "External id": 4725680,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359464684.219, "dur": 2.065, + "args": { + "External id": 4725681,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464685.487, "dur": 0.624, + "args": { + "External id": 4725682,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359464688.193, "dur": 57.120, + "args": { + "External id": 4725683,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359464746.342, "dur": 6.799, + "args": { + "External id": 4725684,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359464746.913, "dur": 5.710, + "args": { + "External id": 4725685,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464750.265, "dur": 2.187, + "args": { + "External id": 4725686,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359464754.477, "dur": 4.875, + "args": { + "External id": 4725687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359464755.510, "dur": 3.385, + "args": { + "External id": 4725688,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464758.369, "dur": 0.462, + "args": { + "External id": 4725689,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359464760.028, "dur": 51.639, + "args": { + "External id": 4725690,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464823.758, "dur": 10.637, + "args": { + "External id": 4725691,"Record function id": 0, "Sequence number": 47018947, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464824.985, "dur": 6.644, + "args": { + "External id": 4725692,"Sequence number": 47018947, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 443 + } + }, + { + "ph": "f", "id": 45, "pid": 1336753, "tid": 1381210, "ts": 1712359464824.985, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359464826.348, "dur": 5.126, + "args": { + "External id": 4725693,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464828.539, "dur": 2.819, + "args": { + "External id": 4725694,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464838.040, "dur": 8.508, + "args": { + "External id": 4725695,"Record function id": 0, "Sequence number": 47018946, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464839.042, "dur": 5.953, + "args": { + "External id": 4725696,"Sequence number": 47018946, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 447 + } + }, + { + "ph": "f", "id": 46, "pid": 1336753, "tid": 1381210, "ts": 1712359464839.042, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359464839.842, "dur": 4.940, + "args": { + "External id": 4725697,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359464840.532, "dur": 3.751, + "args": { + "External id": 4725698,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464843.700, "dur": 0.421, + "args": { + "External id": 4725699,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359464850.223, "dur": 4.236, + "args": { + "External id": 4725700,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359464851.145, "dur": 2.870, + "args": { + "External id": 4725701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359464852.103, "dur": 1.674, + "args": { + "External id": 4725702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359464852.641, "dur": 1.067, + "args": { + "External id": 4725703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464857.459, "dur": 9.962, + "args": { + "External id": 4725704,"Record function id": 0, "Sequence number": 47018945, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359464861.038, "dur": 3.785, + "args": { + "External id": 4725705,"Sequence number": 47018945, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 456 + } + }, + { + "ph": "f", "id": 47, "pid": 1336753, "tid": 1381210, "ts": 1712359464861.038, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359464862.643, "dur": 2.033, + "args": { + "External id": 4725706,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359464863.341, "dur": 1.200, + "args": { + "External id": 4725707,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359464871.982, "dur": 430.389, + "args": { + "External id": 4725708,"Record function id": 0, "Sequence number": 47018944, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359464872.947, "dur": 401.281, + "args": { + "External id": 4725709,"Sequence number": 47018944, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 460 + } + }, + { + "ph": "f", "id": 48, "pid": 1336753, "tid": 1381210, "ts": 1712359464872.947, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359464890.905, "dur": 9.602, + "args": { + "External id": 4725710,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464897.069, "dur": 3.033, + "args": { + "External id": 4725711,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 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": 1336753, "tid": 1381210, + "ts": 1712359464902.621, "dur": 2.927, + "args": { + "External id": 4725712,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464903.461, "dur": 1.896, + "args": { + "External id": 4725713,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 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": 1336753, "tid": 1381210, + "ts": 1712359464907.080, "dur": 6.563, + "args": { + "External id": 4725714,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359464910.252, "dur": 3.223, + "args": { + "External id": 4725715,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 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": 1336753, "tid": 1381210, + "ts": 1712359464957.085, "dur": 288.279, + "args": { + "External id": 4725716,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359465119.715, "dur": 4.980, + "args": { + "External id": 4725717,"Record function id": 0, "Concrete Inputs": ["[16, 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": 1336753, "tid": 1381210, + "ts": 1712359465128.823, "dur": 4.349, + "args": { + "External id": 4725718,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359465260.975, "dur": 4.634, + "args": { + "External id": 4725719,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359465268.369, "dur": 0.733, + "args": { + "External id": 4725720,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359465270.821, "dur": 0.751, + "args": { + "External id": 4725721,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359465313.314, "dur": 252.069, + "args": { + "External id": 4725722,"Record function id": 0, "Sequence number": 47018943, "Fwd thread id": 1, "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359465314.787, "dur": 242.195, + "args": { + "External id": 4725723,"Sequence number": 47018943, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 474 + } + }, + { + "ph": "f", "id": 49, "pid": 1336753, "tid": 1381210, "ts": 1712359465314.787, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359465338.218, "dur": 48.525, + "args": { + "External id": 4725724,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359465345.073, "dur": 3.188, + "args": { + "External id": 4725725,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359465349.355, "dur": 36.746, + "args": { + "External id": 4725726,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359465398.013, "dur": 3.744, + "args": { + "External id": 4725727,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359465399.341, "dur": 2.056, + "args": { + "External id": 4725728,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359465572.101, "dur": 151.468, + "args": { + "External id": 4725729,"Record function id": 0, "Sequence number": 47018942, "Fwd thread id": 1, "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359465573.584, "dur": 143.559, + "args": { + "External id": 4725730,"Sequence number": 47018942, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 481 + } + }, + { + "ph": "f", "id": 50, "pid": 1336753, "tid": 1381210, "ts": 1712359465573.584, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359465585.891, "dur": 32.216, + "args": { + "External id": 4725731,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359465589.842, "dur": 2.518, + "args": { + "External id": 4725732,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359465593.214, "dur": 24.355, + "args": { + "External id": 4725733,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359465625.065, "dur": 4.127, + "args": { + "External id": 4725734,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359465626.483, "dur": 2.403, + "args": { + "External id": 4725735,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465730.020, "dur": 16.384, + "args": { + "External id": 4725736,"Record function id": 0, "Sequence number": 47018941, "Fwd thread id": 1, "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465733.288, "dur": 10.475, + "args": { + "External id": 4725737,"Sequence number": 47018941, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 488 + } + }, + { + "ph": "f", "id": 51, "pid": 1336753, "tid": 1381210, "ts": 1712359465733.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359465735.799, "dur": 7.709, + "args": { + "External id": 4725738,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359465736.911, "dur": 6.405, + "args": { + "External id": 4725739,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465749.861, "dur": 8.920, + "args": { + "External id": 4725740,"Record function id": 0, "Sequence number": 47018940, "Fwd thread id": 1, "Ev Idx": 491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465750.971, "dur": 4.848, + "args": { + "External id": 4725741,"Sequence number": 47018940, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 492 + } + }, + { + "ph": "f", "id": 52, "pid": 1336753, "tid": 1381210, "ts": 1712359465750.971, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359465753.832, "dur": 1.817, + "args": { + "External id": 4725742,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359465754.559, "dur": 0.949, + "args": { + "External id": 4725743,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465761.839, "dur": 8.620, + "args": { + "External id": 4725744,"Record function id": 0, "Sequence number": 47018939, "Fwd thread id": 1, "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465762.754, "dur": 4.797, + "args": { + "External id": 4725745,"Sequence number": 47018939, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 496 + } + }, + { + "ph": "f", "id": 53, "pid": 1336753, "tid": 1381210, "ts": 1712359465762.754, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359465763.988, "dur": 3.412, + "args": { + "External id": 4725746,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359465766.388, "dur": 0.896, + "args": { + "External id": 4725747,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465775.885, "dur": 5.879, + "args": { + "External id": 4725748,"Record function id": 0, "Sequence number": 47018938, "Fwd thread id": 1, "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465776.633, "dur": 2.919, + "args": { + "External id": 4725749,"Sequence number": 47018938, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 500 + } + }, + { + "ph": "f", "id": 54, "pid": 1336753, "tid": 1381210, "ts": 1712359465776.633, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359465777.919, "dur": 1.488, + "args": { + "External id": 4725750,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359465778.524, "dur": 0.751, + "args": { + "External id": 4725751,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465785.084, "dur": 272.910, + "args": { + "External id": 4725752,"Record function id": 0, "Sequence number": 47018937, "Fwd thread id": 1, "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359465786.057, "dur": 260.342, + "args": { + "External id": 4725753,"Sequence number": 47018937, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 504 + } + }, + { + "ph": "f", "id": 55, "pid": 1336753, "tid": 1381210, "ts": 1712359465786.057, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359465791.690, "dur": 8.847, + "args": { + "External id": 4725754,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359465793.906, "dur": 5.945, + "args": { + "External id": 4725755,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359465797.906, "dur": 1.676, + "args": { + "External id": 4725756,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359465802.390, "dur": 68.313, + "args": { + "External id": 4725757,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359465871.833, "dur": 6.313, + "args": { + "External id": 4725758,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359465872.591, "dur": 4.932, + "args": { + "External id": 4725759,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359465876.146, "dur": 1.224, + "args": { + "External id": 4725760,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359465947.371, "dur": 5.799, + "args": { + "External id": 4725761,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359465948.791, "dur": 3.726, + "args": { + "External id": 4725762,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359465951.995, "dur": 0.397, + "args": { + "External id": 4725763,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359465953.882, "dur": 91.071, + "args": { + "External id": 4725764,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466083.271, "dur": 10.713, + "args": { + "External id": 4725765,"Record function id": 0, "Sequence number": 47018936, "Fwd thread id": 1, "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466085.262, "dur": 5.938, + "args": { + "External id": 4725766,"Sequence number": 47018936, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 517 + } + }, + { + "ph": "f", "id": 56, "pid": 1336753, "tid": 1381210, "ts": 1712359466085.262, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359466087.414, "dur": 3.588, + "args": { + "External id": 4725767,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359466088.149, "dur": 2.619, + "args": { + "External id": 4725768,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466098.239, "dur": 12.487, + "args": { + "External id": 4725769,"Record function id": 0, "Sequence number": 47018935, "Fwd thread id": 1, "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466099.241, "dur": 8.468, + "args": { + "External id": 4725770,"Sequence number": 47018935, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 521 + } + }, + { + "ph": "f", "id": 57, "pid": 1336753, "tid": 1381210, "ts": 1712359466099.241, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466102.051, "dur": 5.480, + "args": { + "External id": 4725771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466102.969, "dur": 4.045, + "args": { + "External id": 4725772,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466106.240, "dur": 0.670, + "args": { + "External id": 4725773,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359466116.759, "dur": 10.136, + "args": { + "External id": 4725774,"Record function id": 0, "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359466118.346, "dur": 7.797, + "args": { + "External id": 4725775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359466121.206, "dur": 4.475, + "args": { + "External id": 4725776,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359466122.535, "dur": 2.996, + "args": { + "External id": 4725777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466133.019, "dur": 8.016, + "args": { + "External id": 4725778,"Record function id": 0, "Sequence number": 47018934, "Fwd thread id": 1, "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466133.902, "dur": 4.900, + "args": { + "External id": 4725779,"Sequence number": 47018934, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 530 + } + }, + { + "ph": "f", "id": 58, "pid": 1336753, "tid": 1381210, "ts": 1712359466133.902, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359466135.177, "dur": 3.484, + "args": { + "External id": 4725780,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359466137.514, "dur": 1.016, + "args": { + "External id": 4725781,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466144.304, "dur": 104.943, + "args": { + "External id": 4725782,"Record function id": 0, "Sequence number": 47018933, "Fwd thread id": 1, "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466145.167, "dur": 95.554, + "args": { + "External id": 4725783,"Sequence number": 47018933, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 534 + } + }, + { + "ph": "f", "id": 59, "pid": 1336753, "tid": 1381210, "ts": 1712359466145.167, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466149.262, "dur": 3.800, + "args": { + "External id": 4725784,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466149.818, "dur": 2.843, + "args": { + "External id": 4725785,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466152.212, "dur": 0.342, + "args": { + "External id": 4725786,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359466153.916, "dur": 37.556, + "args": { + "External id": 4725787,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466193.937, "dur": 2.804, + "args": { + "External id": 4725788,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466194.400, "dur": 1.837, + "args": { + "External id": 4725789,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466195.335, "dur": 0.793, + "args": { + "External id": 4725790,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466197.845, "dur": 4.385, + "args": { + "External id": 4725791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466198.429, "dur": 3.414, + "args": { + "External id": 4725792,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466199.158, "dur": 2.618, + "args": { + "External id": 4725793,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359466204.461, "dur": 35.382, + "args": { + "External id": 4725794,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466253.767, "dur": 33.908, + "args": { + "External id": 4725795,"Record function id": 0, "Sequence number": 47018932, "Fwd thread id": 1, "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466254.887, "dur": 5.005, + "args": { + "External id": 4725796,"Sequence number": 47018932, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 547 + } + }, + { + "ph": "f", "id": 60, "pid": 1336753, "tid": 1381210, "ts": 1712359466254.887, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359466258.114, "dur": 1.629, + "args": { + "External id": 4725797,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359466258.553, "dur": 1.065, + "args": { + "External id": 4725798,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1381210, + "ts": 1712359466263.010, "dur": 21.945, + "args": { + "External id": 4725799,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466291.331, "dur": 8.271, + "args": { + "External id": 4725800,"Record function id": 0, "Sequence number": 47018931, "Fwd thread id": 1, "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466292.327, "dur": 5.584, + "args": { + "External id": 4725801,"Sequence number": 47018931, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 552 + } + }, + { + "ph": "f", "id": 61, "pid": 1336753, "tid": 1381210, "ts": 1712359466292.327, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466293.195, "dur": 4.508, + "args": { + "External id": 4725802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466293.813, "dur": 3.360, + "args": { + "External id": 4725803,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466296.482, "dur": 0.539, + "args": { + "External id": 4725804,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359466303.461, "dur": 6.699, + "args": { + "External id": 4725805,"Record function id": 0, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359466306.128, "dur": 3.498, + "args": { + "External id": 4725806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359466307.303, "dur": 1.913, + "args": { + "External id": 4725807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359466307.794, "dur": 1.333, + "args": { + "External id": 4725808,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466313.611, "dur": 6.473, + "args": { + "External id": 4725809,"Record function id": 0, "Sequence number": 47018930, "Fwd thread id": 1, "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466314.812, "dur": 2.908, + "args": { + "External id": 4725810,"Sequence number": 47018930, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 561 + } + }, + { + "ph": "f", "id": 62, "pid": 1336753, "tid": 1381210, "ts": 1712359466314.812, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359466316.177, "dur": 1.398, + "args": { + "External id": 4725811,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359466316.627, "dur": 0.845, + "args": { + "External id": 4725812,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466323.298, "dur": 90.905, + "args": { + "External id": 4725813,"Record function id": 0, "Sequence number": 47018929, "Fwd thread id": 1, "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466324.273, "dur": 79.935, + "args": { + "External id": 4725814,"Sequence number": 47018929, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 565 + } + }, + { + "ph": "f", "id": 63, "pid": 1336753, "tid": 1381210, "ts": 1712359466324.273, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466329.483, "dur": 2.007, + "args": { + "External id": 4725815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466329.938, "dur": 1.117, + "args": { + "External id": 4725816,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466330.551, "dur": 0.409, + "args": { + "External id": 4725817,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359466332.123, "dur": 27.151, + "args": { + "External id": 4725818,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466360.069, "dur": 6.482, + "args": { + "External id": 4725819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466360.617, "dur": 5.480, + "args": { + "External id": 4725820,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466365.490, "dur": 0.509, + "args": { + "External id": 4725821,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466367.599, "dur": 2.829, + "args": { + "External id": 4725822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466368.657, "dur": 1.410, + "args": { + "External id": 4725823,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466369.265, "dur": 0.690, + "args": { + "External id": 4725824,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359466370.836, "dur": 32.577, + "args": { + "External id": 4725825,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466418.372, "dur": 24.790, + "args": { + "External id": 4725826,"Record function id": 0, "Sequence number": 47018928, "Fwd thread id": 1, "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466419.119, "dur": 5.268, + "args": { + "External id": 4725827,"Sequence number": 47018928, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 578 + } + }, + { + "ph": "f", "id": 64, "pid": 1336753, "tid": 1381210, "ts": 1712359466419.119, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359466420.672, "dur": 3.567, + "args": { + "External id": 4725828,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359466423.167, "dur": 0.906, + "args": { + "External id": 4725829,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359466426.507, "dur": 14.506, + "args": { + "External id": 4725830,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466446.711, "dur": 10.955, + "args": { + "External id": 4725831,"Record function id": 0, "Sequence number": 47018927, "Fwd thread id": 1, "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466447.598, "dur": 7.541, + "args": { + "External id": 4725832,"Sequence number": 47018927, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 583 + } + }, + { + "ph": "f", "id": 65, "pid": 1336753, "tid": 1381210, "ts": 1712359466447.598, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466448.531, "dur": 6.397, + "args": { + "External id": 4725833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466451.231, "dur": 3.193, + "args": { + "External id": 4725834,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466453.792, "dur": 0.494, + "args": { + "External id": 4725835,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359466461.517, "dur": 6.568, + "args": { + "External id": 4725836,"Record function id": 0, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359466462.660, "dur": 4.938, + "args": { + "External id": 4725837,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359466463.534, "dur": 3.693, + "args": { + "External id": 4725838,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359466466.076, "dur": 1.054, + "args": { + "External id": 4725839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359466472.087, "dur": 361.918, + "args": { + "External id": 4725840,"Record function id": 0, "Sequence number": 47018926, "Fwd thread id": 1, "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359466473.183, "dur": 331.010, + "args": { + "External id": 4725841,"Sequence number": 47018926, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 592 + } + }, + { + "ph": "f", "id": 66, "pid": 1336753, "tid": 1381210, "ts": 1712359466473.183, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359466509.208, "dur": 1.586, + "args": { + "External id": 4725842,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359466509.702, "dur": 0.946, + "args": { + "External id": 4725843,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359466526.689, "dur": 5.677, + "args": { + "External id": 4725844,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359466542.296, "dur": 2.060, + "args": { + "External id": 4725845,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359466704.871, "dur": 1.506, + "args": { + "External id": 4725846,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359466710.332, "dur": 36.165, + "args": { + "External id": 4725847,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466723.271, "dur": 0.693, + "args": { + "External id": 4725848,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359466752.068, "dur": 27.253, + "args": { + "External id": 4725849,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359466754.150, "dur": 24.937, + "args": { + "External id": 4725850,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466757.573, "dur": 3.996, + "args": { + "External id": 4725851,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359466762.964, "dur": 15.575, + "args": { + "External id": 4725852,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359466785.313, "dur": 1.992, + "args": { + "External id": 4725853,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359466786.276, "dur": 0.934, + "args": { + "External id": 4725854,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359466793.974, "dur": 3.423, + "args": { + "External id": 4725855,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359466796.481, "dur": 0.822, + "args": { + "External id": 4725856,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1381210, + "ts": 1712359466813.744, "dur": 14.991, + "args": { + "External id": 4725857,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359466842.750, "dur": 8.869, + "args": { + "External id": 4725858,"Record function id": 0, "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359466844.337, "dur": 6.653, + "args": { + "External id": 4725859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359466845.853, "dur": 4.186, + "args": { + "External id": 4725860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359466848.439, "dur": 1.440, + "args": { + "External id": 4725861,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466857.576, "dur": 6.362, + "args": { + "External id": 4725862,"Record function id": 0, "Sequence number": 47018925, "Fwd thread id": 1, "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359466859.104, "dur": 1.080, + "args": { + "External id": 4725863,"Sequence number": 47018925, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 614 + } + }, + { + "ph": "f", "id": 67, "pid": 1336753, "tid": 1381210, "ts": 1712359466859.104, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359466867.634, "dur": 469.984, + "args": { + "External id": 4725864,"Record function id": 0, "Sequence number": 47018924, "Fwd thread id": 1, "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359466868.644, "dur": 453.730, + "args": { + "External id": 4725865,"Sequence number": 47018924, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 616 + } + }, + { + "ph": "f", "id": 68, "pid": 1336753, "tid": 1381210, "ts": 1712359466868.644, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359466899.248, "dur": 7.740, + "args": { + "External id": 4725866,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359466903.878, "dur": 2.878, + "args": { + "External id": 4725867,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]", "[8192, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[33554432, 8192, 1], [], []], "Input Dims": [[16, 4096, 2048], [], []], "Ev Idx": 618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466910.221, "dur": 9.815, + "args": { + "External id": 4725868,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466911.397, "dur": 8.092, + "args": { + "External id": 4725869,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466916.594, "dur": 2.741, + "args": { + "External id": 4725870,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1381210, + "ts": 1712359466923.320, "dur": 118.662, + "args": { + "External id": 4725871,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8192, 1], [1, 5632], []], "Input Dims": [[65536, 2048], [5632, 2048], []], "Ev Idx": 622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359466924.034, "dur": 1.911, + "args": { + "External id": 4725872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 5632]], "Input Dims": [[5632, 2048]], "Ev Idx": 623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359466924.481, "dur": 1.054, + "args": { + "External id": 4725873,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 5632], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359466925.086, "dur": 0.374, + "args": { + "External id": 4725874,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[5632, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 5632], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1381210, + "ts": 1712359466926.957, "dur": 114.201, + "args": { + "External id": 4725875,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359466930.279, "dur": 109.638, + "args": { + "External id": 4725876,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359467047.350, "dur": 3.049, + "args": { + "External id": 4725877,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [23068672, 5632, 1]], "Input Dims": [[65536, 5632], [16, 4096, 5632]], "Ev Idx": 628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467048.567, "dur": 1.729, + "args": { + "External id": 4725878,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359467101.258, "dur": 6.048, + "args": { + "External id": 4725879,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359467108.511, "dur": 2.213, + "args": { + "External id": 4725880,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359467111.571, "dur": 1.560, + "args": { + "External id": 4725881,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359467149.912, "dur": 2.274, + "args": { + "External id": 4725882,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467150.556, "dur": 1.403, + "args": { + "External id": 4725883,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 1336753, "tid": 1381210, + "ts": 1712359467178.108, "dur": 125.512, + "args": { + "External id": 4725884,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[8192, 1], [5632, 1]], []], "Input Dims": [[], [[65536, 2048], [65536, 5632]], []], "Ev Idx": 635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1381210, + "ts": 1712359467183.350, "dur": 6.582, + "args": { + "External id": 4725885,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467186.367, "dur": 2.835, + "args": { + "External id": 4725886,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048, 1]", "[8192, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359467191.218, "dur": 7.317, + "args": { + "External id": 4725887,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8192, 1, 1], []], "Input Dims": [[65536, 2048, 1], []], "Ev Idx": 638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467197.445, "dur": 0.477, + "args": { + "External id": 4725888,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 65536]", "[1, 1, 8192]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[65536, 2048, 1], [], [], []], "Ev Idx": 639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1381210, + "ts": 1712359467200.043, "dur": 3.630, + "args": { + "External id": 4725889,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467202.966, "dur": 0.419, + "args": { + "External id": 4725890,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359467204.250, "dur": 3.826, + "args": { + "External id": 4725891,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467207.042, "dur": 0.457, + "args": { + "External id": 4725892,"Record function id": 0, "Concrete Inputs": ["", "[1, 5632, 65536]", "[1, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1, 1], [], [], []], "Input Dims": [[65536, 5632, 1], [], [], []], "Ev Idx": 643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359467213.119, "dur": 1.798, + "args": { + "External id": 4725893,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 8192], []], "Input Dims": [[2048, 1, 65536], []], "Ev Idx": 644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467214.028, "dur": 0.591, + "args": { + "External id": 4725894,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536, 1]", "[1, 8192, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 8192], [], [], []], "Input Dims": [[2048, 1, 65536], [], [], []], "Ev Idx": 645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359467217.438, "dur": 5.173, + "args": { + "External id": 4725895,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 8192, 1], []], "Input Dims": [[2048, 65536, 1], []], "Ev Idx": 646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359467220.317, "dur": 2.127, + "args": { + "External id": 4725896,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]", "[2048, 1, 8192]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 8192, 1], [], []], "Input Dims": [[2048, 65536, 1], [], []], "Ev Idx": 647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359467225.125, "dur": 1.314, + "args": { + "External id": 4725897,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 5632], []], "Input Dims": [[1, 5632, 65536], []], "Ev Idx": 648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467225.810, "dur": 0.333, + "args": { + "External id": 4725898,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 5632], [], [], []], "Input Dims": [[1, 5632, 65536], [], [], []], "Ev Idx": 649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359467226.965, "dur": 5.160, + "args": { + "External id": 4725899,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467229.155, "dur": 2.877, + "args": { + "External id": 4725900,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359467233.887, "dur": 56.538, + "args": { + "External id": 4725901,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1, 8192], [369098752, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632]], "Ev Idx": 652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467294.015, "dur": 1.263, + "args": { + "External id": 4725902,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 5632, 1], []], "Input Dims": [[1, 2048, 5632], []], "Ev Idx": 653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359467295.798, "dur": 3.778, + "args": { + "External id": 4725903,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 5632, 1], []], "Input Dims": [[2048, 1, 5632], []], "Ev Idx": 654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467298.627, "dur": 0.398, + "args": { + "External id": 4725904,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632, 1]", "[5632, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 5632, 1], [], [], []], "Input Dims": [[2048, 1, 5632], [], [], []], "Ev Idx": 655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467301.716, "dur": 0.763, + "args": { + "External id": 4725905,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 5632], []], "Input Dims": [[2048, 5632, 1], []], "Ev Idx": 656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359467348.647, "dur": 8.661, + "args": { + "External id": 4725906,"Record function id": 0, "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359467350.538, "dur": 6.138, + "args": { + "External id": 4725907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359467352.580, "dur": 2.969, + "args": { + "External id": 4725908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359467353.370, "dur": 2.068, + "args": { + "External id": 4725909,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467361.366, "dur": 9.037, + "args": { + "External id": 4725910,"Record function id": 0, "Sequence number": 47018923, "Fwd thread id": 1, "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467362.279, "dur": 5.691, + "args": { + "External id": 4725911,"Sequence number": 47018923, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 662 + } + }, + { + "ph": "f", "id": 69, "pid": 1336753, "tid": 1381210, "ts": 1712359467362.279, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359467364.093, "dur": 3.681, + "args": { + "External id": 4725912,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467366.845, "dur": 0.779, + "args": { + "External id": 4725913,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467373.832, "dur": 121.291, + "args": { + "External id": 4725914,"Record function id": 0, "Sequence number": 47018922, "Fwd thread id": 1, "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467374.910, "dur": 113.263, + "args": { + "External id": 4725915,"Sequence number": 47018922, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 666 + } + }, + { + "ph": "f", "id": 70, "pid": 1336753, "tid": 1381210, "ts": 1712359467374.910, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359467378.600, "dur": 5.159, + "args": { + "External id": 4725916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359467379.579, "dur": 3.632, + "args": { + "External id": 4725917,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467382.417, "dur": 0.610, + "args": { + "External id": 4725918,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359467384.902, "dur": 39.450, + "args": { + "External id": 4725919,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359467427.809, "dur": 3.275, + "args": { + "External id": 4725920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359467428.393, "dur": 1.767, + "args": { + "External id": 4725921,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467429.303, "dur": 0.712, + "args": { + "External id": 4725922,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359467432.907, "dur": 4.465, + "args": { + "External id": 4725923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359467433.862, "dur": 2.992, + "args": { + "External id": 4725924,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467434.397, "dur": 2.386, + "args": { + "External id": 4725925,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359467440.131, "dur": 47.251, + "args": { + "External id": 4725926,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467499.864, "dur": 8.233, + "args": { + "External id": 4725927,"Record function id": 0, "Sequence number": 47018921, "Fwd thread id": 1, "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467500.745, "dur": 5.633, + "args": { + "External id": 4725928,"Sequence number": 47018921, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 679 + } + }, + { + "ph": "f", "id": 71, "pid": 1336753, "tid": 1381210, "ts": 1712359467500.745, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359467504.147, "dur": 2.084, + "args": { + "External id": 4725929,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467504.884, "dur": 1.220, + "args": { + "External id": 4725930,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467511.386, "dur": 7.258, + "args": { + "External id": 4725931,"Record function id": 0, "Sequence number": 47018920, "Fwd thread id": 1, "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467512.305, "dur": 3.789, + "args": { + "External id": 4725932,"Sequence number": 47018920, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 683 + } + }, + { + "ph": "f", "id": 72, "pid": 1336753, "tid": 1381210, "ts": 1712359467512.305, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359467513.391, "dur": 2.503, + "args": { + "External id": 4725933,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359467514.100, "dur": 1.328, + "args": { + "External id": 4725934,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467514.786, "dur": 0.535, + "args": { + "External id": 4725935,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359467522.353, "dur": 6.599, + "args": { + "External id": 4725936,"Record function id": 0, "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359467523.396, "dur": 5.059, + "args": { + "External id": 4725937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359467524.689, "dur": 3.286, + "args": { + "External id": 4725938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359467526.692, "dur": 1.204, + "args": { + "External id": 4725939,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467532.195, "dur": 8.071, + "args": { + "External id": 4725940,"Record function id": 0, "Sequence number": 47018919, "Fwd thread id": 1, "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467535.117, "dur": 2.580, + "args": { + "External id": 4725941,"Sequence number": 47018919, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 692 + } + }, + { + "ph": "f", "id": 73, "pid": 1336753, "tid": 1381210, "ts": 1712359467535.117, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359467536.056, "dur": 1.498, + "args": { + "External id": 4725942,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467536.577, "dur": 0.840, + "args": { + "External id": 4725943,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467543.496, "dur": 128.148, + "args": { + "External id": 4725944,"Record function id": 0, "Sequence number": 47018918, "Fwd thread id": 1, "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467544.370, "dur": 117.616, + "args": { + "External id": 4725945,"Sequence number": 47018918, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 696 + } + }, + { + "ph": "f", "id": 74, "pid": 1336753, "tid": 1381210, "ts": 1712359467544.370, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359467548.078, "dur": 17.479, + "args": { + "External id": 4725946,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359467550.045, "dur": 14.997, + "args": { + "External id": 4725947,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467564.078, "dur": 0.705, + "args": { + "External id": 4725948,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359467566.244, "dur": 34.821, + "args": { + "External id": 4725949,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359467602.198, "dur": 6.050, + "args": { + "External id": 4725950,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359467602.700, "dur": 4.955, + "args": { + "External id": 4725951,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467603.618, "dur": 3.895, + "args": { + "External id": 4725952,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359467611.196, "dur": 4.580, + "args": { + "External id": 4725953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359467611.959, "dur": 3.197, + "args": { + "External id": 4725954,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467614.573, "dur": 0.519, + "args": { + "External id": 4725955,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359467616.349, "dur": 44.902, + "args": { + "External id": 4725956,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467676.317, "dur": 28.651, + "args": { + "External id": 4725957,"Record function id": 0, "Sequence number": 47018917, "Fwd thread id": 1, "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467677.254, "dur": 3.195, + "args": { + "External id": 4725958,"Sequence number": 47018917, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 709 + } + }, + { + "ph": "f", "id": 75, "pid": 1336753, "tid": 1381210, "ts": 1712359467677.254, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359467678.465, "dur": 1.834, + "args": { + "External id": 4725959,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467678.991, "dur": 1.145, + "args": { + "External id": 4725960,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1381210, + "ts": 1712359467683.063, "dur": 19.020, + "args": { + "External id": 4725961,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467708.760, "dur": 11.814, + "args": { + "External id": 4725962,"Record function id": 0, "Sequence number": 47018916, "Fwd thread id": 1, "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359467712.047, "dur": 6.031, + "args": { + "External id": 4725963,"Sequence number": 47018916, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 714 + } + }, + { + "ph": "f", "id": 76, "pid": 1336753, "tid": 1381210, "ts": 1712359467712.047, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359467713.147, "dur": 4.715, + "args": { + "External id": 4725964,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359467713.658, "dur": 3.683, + "args": { + "External id": 4725965,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359467716.767, "dur": 0.448, + "args": { + "External id": 4725966,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359467724.261, "dur": 4.532, + "args": { + "External id": 4725967,"Record function id": 0, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359467725.409, "dur": 2.877, + "args": { + "External id": 4725968,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359467726.338, "dur": 1.519, + "args": { + "External id": 4725969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359467726.821, "dur": 0.967, + "args": { + "External id": 4725970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359467734.753, "dur": 480.266, + "args": { + "External id": 4725971,"Record function id": 0, "Sequence number": 47018915, "Fwd thread id": 1, "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359467735.980, "dur": 442.065, + "args": { + "External id": 4725972,"Sequence number": 47018915, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 723 + } + }, + { + "ph": "f", "id": 77, "pid": 1336753, "tid": 1381210, "ts": 1712359467735.980, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1712359467757.548, "dur": 32.196, + "args": { + "External id": 4725973,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359467758.832, "dur": 30.712, + "args": { + "External id": 4725974,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359467761.298, "dur": 6.917, + "args": { + "External id": 4725975,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359467765.209, "dur": 2.521, + "args": { + "External id": 4725976,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359467769.475, "dur": 19.642, + "args": { + "External id": 4725977,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359467802.570, "dur": 3.953, + "args": { + "External id": 4725978,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467803.044, "dur": 3.331, + "args": { + "External id": 4725979,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359467810.515, "dur": 1.573, + "args": { + "External id": 4725980,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359467811.186, "dur": 0.761, + "args": { + "External id": 4725981,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359467825.186, "dur": 1.897, + "args": { + "External id": 4725982,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359467837.388, "dur": 1.983, + "args": { + "External id": 4725983,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359468040.709, "dur": 3.993, + "args": { + "External id": 4725984,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359468049.005, "dur": 52.286, + "args": { + "External id": 4725985,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468059.118, "dur": 1.099, + "args": { + "External id": 4725986,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359468109.128, "dur": 32.295, + "args": { + "External id": 4725987,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359468110.762, "dur": 30.404, + "args": { + "External id": 4725988,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468116.553, "dur": 5.187, + "args": { + "External id": 4725989,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359468125.039, "dur": 15.708, + "args": { + "External id": 4725990,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359468146.055, "dur": 2.598, + "args": { + "External id": 4725991,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359468147.071, "dur": 1.432, + "args": { + "External id": 4725992,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359468156.552, "dur": 4.044, + "args": { + "External id": 4725993,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359468157.155, "dur": 3.323, + "args": { + "External id": 4725994,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359468164.255, "dur": 1.469, + "args": { + "External id": 4725995,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359468164.690, "dur": 0.947, + "args": { + "External id": 4725996,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359468196.666, "dur": 16.764, + "args": { + "External id": 4725997,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359468229.849, "dur": 8.294, + "args": { + "External id": 4725998,"Record function id": 0, "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359468231.712, "dur": 5.712, + "args": { + "External id": 4725999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359468233.602, "dur": 2.883, + "args": { + "External id": 4726000,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359468234.366, "dur": 1.958, + "args": { + "External id": 4726001,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468242.305, "dur": 8.331, + "args": { + "External id": 4726002,"Record function id": 0, "Sequence number": 47018914, "Fwd thread id": 1, "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468243.335, "dur": 4.133, + "args": { + "External id": 4726003,"Sequence number": 47018914, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 754 + } + }, + { + "ph": "f", "id": 78, "pid": 1336753, "tid": 1381210, "ts": 1712359468243.335, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359468245.141, "dur": 2.114, + "args": { + "External id": 4726004,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359468245.766, "dur": 1.331, + "args": { + "External id": 4726005,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468256.692, "dur": 134.339, + "args": { + "External id": 4726006,"Record function id": 0, "Sequence number": 47018913, "Fwd thread id": 1, "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468257.549, "dur": 125.214, + "args": { + "External id": 4726007,"Sequence number": 47018913, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 758 + } + }, + { + "ph": "f", "id": 79, "pid": 1336753, "tid": 1381210, "ts": 1712359468257.549, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359468262.167, "dur": 6.178, + "args": { + "External id": 4726008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359468263.586, "dur": 4.097, + "args": { + "External id": 4726009,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468266.585, "dur": 0.914, + "args": { + "External id": 4726010,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359468269.570, "dur": 57.144, + "args": { + "External id": 4726011,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359468327.835, "dur": 7.422, + "args": { + "External id": 4726012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359468330.745, "dur": 3.801, + "args": { + "External id": 4726013,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468331.619, "dur": 2.757, + "args": { + "External id": 4726014,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359468337.376, "dur": 3.077, + "args": { + "External id": 4726015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359468338.736, "dur": 1.259, + "args": { + "External id": 4726016,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468339.490, "dur": 0.368, + "args": { + "External id": 4726017,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359468340.924, "dur": 41.135, + "args": { + "External id": 4726018,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468395.793, "dur": 12.902, + "args": { + "External id": 4726019,"Record function id": 0, "Sequence number": 47018912, "Fwd thread id": 1, "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468399.115, "dur": 6.479, + "args": { + "External id": 4726020,"Sequence number": 47018912, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 771 + } + }, + { + "ph": "f", "id": 80, "pid": 1336753, "tid": 1381210, "ts": 1712359468399.115, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359468402.110, "dur": 3.337, + "args": { + "External id": 4726021,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359468402.574, "dur": 2.709, + "args": { + "External id": 4726022,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468414.782, "dur": 6.497, + "args": { + "External id": 4726023,"Record function id": 0, "Sequence number": 47018911, "Fwd thread id": 1, "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468415.970, "dur": 3.708, + "args": { + "External id": 4726024,"Sequence number": 47018911, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 775 + } + }, + { + "ph": "f", "id": 81, "pid": 1336753, "tid": 1381210, "ts": 1712359468415.970, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359468416.891, "dur": 2.584, + "args": { + "External id": 4726025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359468417.627, "dur": 1.308, + "args": { + "External id": 4726026,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468418.373, "dur": 0.423, + "args": { + "External id": 4726027,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359468425.361, "dur": 6.693, + "args": { + "External id": 4726028,"Record function id": 0, "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359468426.511, "dur": 5.003, + "args": { + "External id": 4726029,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359468427.402, "dur": 3.843, + "args": { + "External id": 4726030,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359468429.998, "dur": 1.173, + "args": { + "External id": 4726031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468435.486, "dur": 8.223, + "args": { + "External id": 4726032,"Record function id": 0, "Sequence number": 47018910, "Fwd thread id": 1, "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359468436.365, "dur": 4.949, + "args": { + "External id": 4726033,"Sequence number": 47018910, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 784 + } + }, + { + "ph": "f", "id": 82, "pid": 1336753, "tid": 1381210, "ts": 1712359468436.365, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359468437.511, "dur": 3.649, + "args": { + "External id": 4726034,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359468439.929, "dur": 1.090, + "args": { + "External id": 4726035,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359468447.918, "dur": 281.821, + "args": { + "External id": 4726036,"Record function id": 0, "Sequence number": 47018909, "Fwd thread id": 1, "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359468449.005, "dur": 258.081, + "args": { + "External id": 4726037,"Sequence number": 47018909, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 788 + } + }, + { + "ph": "f", "id": 83, "pid": 1336753, "tid": 1381210, "ts": 1712359468449.005, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359468466.414, "dur": 5.564, + "args": { + "External id": 4726038,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468468.508, "dur": 3.092, + "args": { + "External id": 4726039,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359468473.944, "dur": 4.487, + "args": { + "External id": 4726040,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468476.477, "dur": 1.790, + "args": { + "External id": 4726041,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359468479.719, "dur": 4.354, + "args": { + "External id": 4726042,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468480.543, "dur": 3.364, + "args": { + "External id": 4726043,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359468509.448, "dur": 173.501, + "args": { + "External id": 4726044,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359468591.578, "dur": 3.484, + "args": { + "External id": 4726045,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359468596.624, "dur": 3.441, + "args": { + "External id": 4726046,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359468694.536, "dur": 3.542, + "args": { + "External id": 4726047,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359468700.923, "dur": 0.743, + "args": { + "External id": 4726048,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359468703.532, "dur": 0.617, + "args": { + "External id": 4726049,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359468736.357, "dur": 216.326, + "args": { + "External id": 4726050,"Record function id": 0, "Sequence number": 47018908, "Fwd thread id": 1, "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359468737.516, "dur": 207.539, + "args": { + "External id": 4726051,"Sequence number": 47018908, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 802 + } + }, + { + "ph": "f", "id": 84, "pid": 1336753, "tid": 1381210, "ts": 1712359468737.516, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359468756.240, "dur": 40.657, + "args": { + "External id": 4726052,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468758.709, "dur": 2.818, + "args": { + "External id": 4726053,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359468762.631, "dur": 33.680, + "args": { + "External id": 4726054,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359468805.692, "dur": 5.595, + "args": { + "External id": 4726055,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468809.089, "dur": 1.915, + "args": { + "External id": 4726056,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359468959.329, "dur": 221.368, + "args": { + "External id": 4726057,"Record function id": 0, "Sequence number": 47018907, "Fwd thread id": 1, "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359468960.759, "dur": 211.908, + "args": { + "External id": 4726058,"Sequence number": 47018907, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 809 + } + }, + { + "ph": "f", "id": 85, "pid": 1336753, "tid": 1381210, "ts": 1712359468960.759, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359468973.788, "dur": 71.817, + "args": { + "External id": 4726059,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359468975.668, "dur": 2.497, + "args": { + "External id": 4726060,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359468979.073, "dur": 65.709, + "args": { + "External id": 4726061,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359469054.451, "dur": 8.911, + "args": { + "External id": 4726062,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469059.868, "dur": 3.218, + "args": { + "External id": 4726063,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469189.845, "dur": 17.409, + "args": { + "External id": 4726064,"Record function id": 0, "Sequence number": 47018906, "Fwd thread id": 1, "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469193.257, "dur": 10.914, + "args": { + "External id": 4726065,"Sequence number": 47018906, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 816 + } + }, + { + "ph": "f", "id": 86, "pid": 1336753, "tid": 1381210, "ts": 1712359469193.257, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469196.268, "dur": 7.573, + "args": { + "External id": 4726066,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469197.309, "dur": 6.351, + "args": { + "External id": 4726067,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469210.948, "dur": 8.450, + "args": { + "External id": 4726068,"Record function id": 0, "Sequence number": 47018905, "Fwd thread id": 1, "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469211.850, "dur": 4.563, + "args": { + "External id": 4726069,"Sequence number": 47018905, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 820 + } + }, + { + "ph": "f", "id": 87, "pid": 1336753, "tid": 1381210, "ts": 1712359469211.850, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469212.985, "dur": 3.248, + "args": { + "External id": 4726070,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469215.271, "dur": 0.840, + "args": { + "External id": 4726071,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469224.267, "dur": 7.701, + "args": { + "External id": 4726072,"Record function id": 0, "Sequence number": 47018904, "Fwd thread id": 1, "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469225.126, "dur": 4.599, + "args": { + "External id": 4726073,"Sequence number": 47018904, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 824 + } + }, + { + "ph": "f", "id": 88, "pid": 1336753, "tid": 1381210, "ts": 1712359469225.126, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469226.054, "dur": 3.534, + "args": { + "External id": 4726074,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469228.461, "dur": 0.991, + "args": { + "External id": 4726075,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469235.375, "dur": 8.943, + "args": { + "External id": 4726076,"Record function id": 0, "Sequence number": 47018903, "Fwd thread id": 1, "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469236.265, "dur": 4.921, + "args": { + "External id": 4726077,"Sequence number": 47018903, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 828 + } + }, + { + "ph": "f", "id": 89, "pid": 1336753, "tid": 1381210, "ts": 1712359469236.265, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469237.586, "dur": 3.427, + "args": { + "External id": 4726078,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469240.010, "dur": 0.882, + "args": { + "External id": 4726079,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469247.743, "dur": 150.382, + "args": { + "External id": 4726080,"Record function id": 0, "Sequence number": 47018902, "Fwd thread id": 1, "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469248.565, "dur": 141.437, + "args": { + "External id": 4726081,"Sequence number": 47018902, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 832 + } + }, + { + "ph": "f", "id": 90, "pid": 1336753, "tid": 1381210, "ts": 1712359469248.565, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469253.808, "dur": 8.498, + "args": { + "External id": 4726082,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469255.834, "dur": 5.807, + "args": { + "External id": 4726083,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469259.806, "dur": 1.548, + "args": { + "External id": 4726084,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359469263.950, "dur": 64.606, + "args": { + "External id": 4726085,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469329.903, "dur": 4.353, + "args": { + "External id": 4726086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469330.558, "dur": 2.850, + "args": { + "External id": 4726087,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469331.971, "dur": 1.290, + "args": { + "External id": 4726088,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469335.958, "dur": 8.114, + "args": { + "External id": 4726089,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469337.496, "dur": 6.004, + "args": { + "External id": 4726090,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469342.596, "dur": 0.805, + "args": { + "External id": 4726091,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359469344.847, "dur": 44.278, + "args": { + "External id": 4726092,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469402.657, "dur": 7.122, + "args": { + "External id": 4726093,"Record function id": 0, "Sequence number": 47018901, "Fwd thread id": 1, "Ev Idx": 844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469403.724, "dur": 3.705, + "args": { + "External id": 4726094,"Sequence number": 47018901, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 845 + } + }, + { + "ph": "f", "id": 91, "pid": 1336753, "tid": 1381210, "ts": 1712359469403.724, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469405.148, "dur": 2.147, + "args": { + "External id": 4726095,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469405.873, "dur": 1.283, + "args": { + "External id": 4726096,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469413.245, "dur": 8.226, + "args": { + "External id": 4726097,"Record function id": 0, "Sequence number": 47018900, "Fwd thread id": 1, "Ev Idx": 848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469414.039, "dur": 5.648, + "args": { + "External id": 4726098,"Sequence number": 47018900, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 849 + } + }, + { + "ph": "f", "id": 92, "pid": 1336753, "tid": 1381210, "ts": 1712359469414.039, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469414.917, "dur": 4.574, + "args": { + "External id": 4726099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469417.713, "dur": 1.281, + "args": { + "External id": 4726100,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469418.525, "dur": 0.361, + "args": { + "External id": 4726101,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359469429.629, "dur": 8.847, + "args": { + "External id": 4726102,"Record function id": 0, "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359469431.009, "dur": 6.719, + "args": { + "External id": 4726103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359469433.539, "dur": 3.810, + "args": { + "External id": 4726104,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359469434.682, "dur": 2.564, + "args": { + "External id": 4726105,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469441.616, "dur": 5.593, + "args": { + "External id": 4726106,"Record function id": 0, "Sequence number": 47018899, "Fwd thread id": 1, "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469442.400, "dur": 2.725, + "args": { + "External id": 4726107,"Sequence number": 47018899, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 858 + } + }, + { + "ph": "f", "id": 93, "pid": 1336753, "tid": 1381210, "ts": 1712359469442.400, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469443.653, "dur": 1.342, + "args": { + "External id": 4726108,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469444.102, "dur": 0.767, + "args": { + "External id": 4726109,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469452.182, "dur": 84.940, + "args": { + "External id": 4726110,"Record function id": 0, "Sequence number": 47018898, "Fwd thread id": 1, "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469453.017, "dur": 77.735, + "args": { + "External id": 4726111,"Sequence number": 47018898, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 862 + } + }, + { + "ph": "f", "id": 94, "pid": 1336753, "tid": 1381210, "ts": 1712359469453.017, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469456.255, "dur": 2.077, + "args": { + "External id": 4726112,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469456.813, "dur": 1.102, + "args": { + "External id": 4726113,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469457.515, "dur": 0.286, + "args": { + "External id": 4726114,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359469459.121, "dur": 24.390, + "args": { + "External id": 4726115,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469484.482, "dur": 6.397, + "args": { + "External id": 4726116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469486.900, "dur": 3.495, + "args": { + "External id": 4726117,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469489.553, "dur": 0.727, + "args": { + "External id": 4726118,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469491.810, "dur": 4.386, + "args": { + "External id": 4726119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469492.933, "dur": 2.738, + "args": { + "External id": 4726120,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469493.696, "dur": 1.906, + "args": { + "External id": 4726121,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359469496.782, "dur": 33.245, + "args": { + "External id": 4726122,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469541.423, "dur": 34.762, + "args": { + "External id": 4726123,"Record function id": 0, "Sequence number": 47018897, "Fwd thread id": 1, "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469544.587, "dur": 5.290, + "args": { + "External id": 4726124,"Sequence number": 47018897, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 875 + } + }, + { + "ph": "f", "id": 95, "pid": 1336753, "tid": 1381210, "ts": 1712359469544.587, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469546.015, "dur": 3.738, + "args": { + "External id": 4726125,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469548.510, "dur": 1.122, + "args": { + "External id": 4726126,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1381210, + "ts": 1712359469552.800, "dur": 21.392, + "args": { + "External id": 4726127,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469580.249, "dur": 7.960, + "args": { + "External id": 4726128,"Record function id": 0, "Sequence number": 47018896, "Fwd thread id": 1, "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469581.199, "dur": 5.377, + "args": { + "External id": 4726129,"Sequence number": 47018896, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 880 + } + }, + { + "ph": "f", "id": 96, "pid": 1336753, "tid": 1381210, "ts": 1712359469581.199, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469581.826, "dur": 4.532, + "args": { + "External id": 4726130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469582.446, "dur": 3.437, + "args": { + "External id": 4726131,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469585.342, "dur": 0.430, + "args": { + "External id": 4726132,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359469591.952, "dur": 4.901, + "args": { + "External id": 4726133,"Record function id": 0, "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359469593.108, "dur": 3.207, + "args": { + "External id": 4726134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359469594.463, "dur": 1.453, + "args": { + "External id": 4726135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359469595.074, "dur": 0.730, + "args": { + "External id": 4726136,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469600.126, "dur": 7.485, + "args": { + "External id": 4726137,"Record function id": 0, "Sequence number": 47018895, "Fwd thread id": 1, "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469601.109, "dur": 4.403, + "args": { + "External id": 4726138,"Sequence number": 47018895, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 889 + } + }, + { + "ph": "f", "id": 97, "pid": 1336753, "tid": 1381210, "ts": 1712359469601.109, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469602.337, "dur": 3.017, + "args": { + "External id": 4726139,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469604.537, "dur": 0.724, + "args": { + "External id": 4726140,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469612.626, "dur": 93.716, + "args": { + "External id": 4726141,"Record function id": 0, "Sequence number": 47018894, "Fwd thread id": 1, "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469615.254, "dur": 81.240, + "args": { + "External id": 4726142,"Sequence number": 47018894, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 893 + } + }, + { + "ph": "f", "id": 98, "pid": 1336753, "tid": 1381210, "ts": 1712359469615.254, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469618.346, "dur": 2.231, + "args": { + "External id": 4726143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469618.912, "dur": 1.237, + "args": { + "External id": 4726144,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469619.512, "dur": 0.523, + "args": { + "External id": 4726145,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359469621.200, "dur": 26.620, + "args": { + "External id": 4726146,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469648.725, "dur": 4.574, + "args": { + "External id": 4726147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469649.180, "dur": 3.612, + "args": { + "External id": 4726148,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469651.779, "dur": 0.897, + "args": { + "External id": 4726149,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469654.847, "dur": 6.809, + "args": { + "External id": 4726150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469658.401, "dur": 2.710, + "args": { + "External id": 4726151,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469660.636, "dur": 0.353, + "args": { + "External id": 4726152,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359469662.251, "dur": 33.449, + "args": { + "External id": 4726153,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469710.440, "dur": 25.151, + "args": { + "External id": 4726154,"Record function id": 0, "Sequence number": 47018893, "Fwd thread id": 1, "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469711.453, "dur": 5.104, + "args": { + "External id": 4726155,"Sequence number": 47018893, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 906 + } + }, + { + "ph": "f", "id": 99, "pid": 1336753, "tid": 1381210, "ts": 1712359469711.453, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469714.785, "dur": 1.620, + "args": { + "External id": 4726156,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469715.249, "dur": 1.036, + "args": { + "External id": 4726157,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359469719.158, "dur": 14.128, + "args": { + "External id": 4726158,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469739.187, "dur": 9.478, + "args": { + "External id": 4726159,"Record function id": 0, "Sequence number": 47018892, "Fwd thread id": 1, "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359469740.116, "dur": 5.789, + "args": { + "External id": 4726160,"Sequence number": 47018892, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 911 + } + }, + { + "ph": "f", "id": 100, "pid": 1336753, "tid": 1381210, "ts": 1712359469740.116, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359469740.885, "dur": 4.842, + "args": { + "External id": 4726161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359469741.586, "dur": 3.555, + "args": { + "External id": 4726162,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359469744.351, "dur": 0.702, + "args": { + "External id": 4726163,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359469752.387, "dur": 7.229, + "args": { + "External id": 4726164,"Record function id": 0, "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359469753.541, "dur": 5.601, + "args": { + "External id": 4726165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359469754.523, "dur": 4.157, + "args": { + "External id": 4726166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359469757.539, "dur": 1.049, + "args": { + "External id": 4726167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359469763.918, "dur": 447.671, + "args": { + "External id": 4726168,"Record function id": 0, "Sequence number": 47018891, "Fwd thread id": 1, "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359469764.975, "dur": 412.816, + "args": { + "External id": 4726169,"Sequence number": 47018891, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 920 + } + }, + { + "ph": "f", "id": 101, "pid": 1336753, "tid": 1381210, "ts": 1712359469764.975, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359469808.120, "dur": 1.960, + "args": { + "External id": 4726170,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469808.819, "dur": 1.147, + "args": { + "External id": 4726171,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359469824.498, "dur": 5.648, + "args": { + "External id": 4726172,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359469840.966, "dur": 1.934, + "args": { + "External id": 4726173,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359469983.782, "dur": 54.912, + "args": { + "External id": 4726174,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359470045.114, "dur": 59.188, + "args": { + "External id": 4726175,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470058.238, "dur": 1.179, + "args": { + "External id": 4726176,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359470115.602, "dur": 34.647, + "args": { + "External id": 4726177,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359470117.431, "dur": 32.603, + "args": { + "External id": 4726178,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470124.047, "dur": 6.557, + "args": { + "External id": 4726179,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359470131.984, "dur": 17.543, + "args": { + "External id": 4726180,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359470157.120, "dur": 2.694, + "args": { + "External id": 4726181,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470158.233, "dur": 1.486, + "args": { + "External id": 4726182,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359470168.041, "dur": 1.931, + "args": { + "External id": 4726183,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470168.797, "dur": 1.068, + "args": { + "External id": 4726184,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359470191.769, "dur": 15.496, + "args": { + "External id": 4726185,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359470226.175, "dur": 13.351, + "args": { + "External id": 4726186,"Record function id": 0, "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359470230.370, "dur": 8.303, + "args": { + "External id": 4726187,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359470232.480, "dur": 5.150, + "args": { + "External id": 4726188,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359470235.499, "dur": 2.050, + "args": { + "External id": 4726189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470243.244, "dur": 8.082, + "args": { + "External id": 4726190,"Record function id": 0, "Sequence number": 47018890, "Fwd thread id": 1, "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470245.076, "dur": 1.634, + "args": { + "External id": 4726191,"Sequence number": 47018890, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 942 + } + }, + { + "ph": "f", "id": 102, "pid": 1336753, "tid": 1381210, "ts": 1712359470245.076, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359470255.115, "dur": 434.672, + "args": { + "External id": 4726192,"Record function id": 0, "Sequence number": 47018889, "Fwd thread id": 1, "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359470256.062, "dur": 421.630, + "args": { + "External id": 4726193,"Sequence number": 47018889, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 944 + } + }, + { + "ph": "f", "id": 103, "pid": 1336753, "tid": 1381210, "ts": 1712359470256.062, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359470286.432, "dur": 7.754, + "args": { + "External id": 4726194,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359470291.036, "dur": 2.885, + "args": { + "External id": 4726195,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]", "[8192, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[33554432, 8192, 1], [], []], "Input Dims": [[16, 4096, 2048], [], []], "Ev Idx": 946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359470297.630, "dur": 10.749, + "args": { + "External id": 4726196,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359470301.168, "dur": 6.398, + "args": { + "External id": 4726197,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470304.401, "dur": 2.991, + "args": { + "External id": 4726198,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1381210, + "ts": 1712359470311.783, "dur": 107.286, + "args": { + "External id": 4726199,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8192, 1], [1, 5632], []], "Input Dims": [[65536, 2048], [5632, 2048], []], "Ev Idx": 950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359470312.651, "dur": 2.286, + "args": { + "External id": 4726200,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 5632]], "Input Dims": [[5632, 2048]], "Ev Idx": 951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359470313.126, "dur": 1.359, + "args": { + "External id": 4726201,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 5632], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470313.759, "dur": 0.651, + "args": { + "External id": 4726202,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[5632, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 5632], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1381210, + "ts": 1712359470317.873, "dur": 100.629, + "args": { + "External id": 4726203,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359470319.217, "dur": 98.310, + "args": { + "External id": 4726204,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359470422.680, "dur": 2.100, + "args": { + "External id": 4726205,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [23068672, 5632, 1]], "Input Dims": [[65536, 5632], [16, 4096, 5632]], "Ev Idx": 956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470423.467, "dur": 1.199, + "args": { + "External id": 4726206,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359470454.047, "dur": 5.595, + "args": { + "External id": 4726207,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359470462.619, "dur": 2.301, + "args": { + "External id": 4726208,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359470465.589, "dur": 2.022, + "args": { + "External id": 4726209,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359470499.856, "dur": 2.060, + "args": { + "External id": 4726210,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470500.645, "dur": 1.131, + "args": { + "External id": 4726211,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 1336753, "tid": 1381210, + "ts": 1712359470524.670, "dur": 137.042, + "args": { + "External id": 4726212,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[8192, 1], [5632, 1]], []], "Input Dims": [[], [[65536, 2048], [65536, 5632]], []], "Ev Idx": 963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1381210, + "ts": 1712359470529.737, "dur": 8.679, + "args": { + "External id": 4726213,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470534.327, "dur": 3.258, + "args": { + "External id": 4726214,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048, 1]", "[8192, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359470539.627, "dur": 7.733, + "args": { + "External id": 4726215,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8192, 1, 1], []], "Input Dims": [[65536, 2048, 1], []], "Ev Idx": 966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470546.127, "dur": 0.517, + "args": { + "External id": 4726216,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 65536]", "[1, 1, 8192]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[65536, 2048, 1], [], [], []], "Ev Idx": 967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1381210, + "ts": 1712359470548.821, "dur": 1.599, + "args": { + "External id": 4726217,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470549.661, "dur": 0.404, + "args": { + "External id": 4726218,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359470552.604, "dur": 2.086, + "args": { + "External id": 4726219,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470553.621, "dur": 0.511, + "args": { + "External id": 4726220,"Record function id": 0, "Concrete Inputs": ["", "[1, 5632, 65536]", "[1, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1, 1], [], [], []], "Input Dims": [[65536, 5632, 1], [], [], []], "Ev Idx": 971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359470561.850, "dur": 1.690, + "args": { + "External id": 4726221,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 8192], []], "Input Dims": [[2048, 1, 65536], []], "Ev Idx": 972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470562.697, "dur": 0.577, + "args": { + "External id": 4726222,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536, 1]", "[1, 8192, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 8192], [], [], []], "Input Dims": [[2048, 1, 65536], [], [], []], "Ev Idx": 973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359470564.153, "dur": 6.027, + "args": { + "External id": 4726223,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 8192, 1], []], "Input Dims": [[2048, 65536, 1], []], "Ev Idx": 974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359470568.144, "dur": 1.878, + "args": { + "External id": 4726224,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]", "[2048, 1, 8192]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 8192, 1], [], []], "Input Dims": [[2048, 65536, 1], [], []], "Ev Idx": 975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359470570.949, "dur": 3.444, + "args": { + "External id": 4726225,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 5632], []], "Input Dims": [[1, 5632, 65536], []], "Ev Idx": 976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470573.821, "dur": 0.320, + "args": { + "External id": 4726226,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 5632], [], [], []], "Input Dims": [[1, 5632, 65536], [], [], []], "Ev Idx": 977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359470574.857, "dur": 4.004, + "args": { + "External id": 4726227,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470575.223, "dur": 3.534, + "args": { + "External id": 4726228,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359470580.229, "dur": 66.491, + "args": { + "External id": 4726229,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1, 8192], [369098752, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632]], "Ev Idx": 980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470651.819, "dur": 1.154, + "args": { + "External id": 4726230,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 5632, 1], []], "Input Dims": [[1, 2048, 5632], []], "Ev Idx": 981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359470653.447, "dur": 3.985, + "args": { + "External id": 4726231,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 5632, 1], []], "Input Dims": [[2048, 1, 5632], []], "Ev Idx": 982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470656.121, "dur": 0.575, + "args": { + "External id": 4726232,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632, 1]", "[5632, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 5632, 1], [], [], []], "Input Dims": [[2048, 1, 5632], [], [], []], "Ev Idx": 983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470659.721, "dur": 0.941, + "args": { + "External id": 4726233,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 5632], []], "Input Dims": [[2048, 5632, 1], []], "Ev Idx": 984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359470698.381, "dur": 7.541, + "args": { + "External id": 4726234,"Record function id": 0, "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359470700.192, "dur": 5.087, + "args": { + "External id": 4726235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359470701.665, "dur": 2.769, + "args": { + "External id": 4726236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359470702.409, "dur": 1.906, + "args": { + "External id": 4726237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470709.718, "dur": 6.896, + "args": { + "External id": 4726238,"Record function id": 0, "Sequence number": 47018888, "Fwd thread id": 1, "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470710.695, "dur": 3.019, + "args": { + "External id": 4726239,"Sequence number": 47018888, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 990 + } + }, + { + "ph": "f", "id": 104, "pid": 1336753, "tid": 1381210, "ts": 1712359470710.695, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359470712.098, "dur": 1.447, + "args": { + "External id": 4726240,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470712.704, "dur": 0.721, + "args": { + "External id": 4726241,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470722.185, "dur": 175.968, + "args": { + "External id": 4726242,"Record function id": 0, "Sequence number": 47018887, "Fwd thread id": 1, "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470723.176, "dur": 166.984, + "args": { + "External id": 4726243,"Sequence number": 47018887, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 994 + } + }, + { + "ph": "f", "id": 105, "pid": 1336753, "tid": 1381210, "ts": 1712359470723.176, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359470726.576, "dur": 3.069, + "args": { + "External id": 4726244,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359470727.583, "dur": 1.556, + "args": { + "External id": 4726245,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470728.390, "dur": 0.610, + "args": { + "External id": 4726246,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359470730.477, "dur": 56.713, + "args": { + "External id": 4726247,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359470788.300, "dur": 8.034, + "args": { + "External id": 4726248,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359470789.012, "dur": 6.581, + "args": { + "External id": 4726249,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470794.166, "dur": 1.241, + "args": { + "External id": 4726250,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359470797.972, "dur": 5.529, + "args": { + "External id": 4726251,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359470799.494, "dur": 3.355, + "args": { + "External id": 4726252,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470800.308, "dur": 2.413, + "args": { + "External id": 4726253,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359470804.131, "dur": 85.166, + "args": { + "External id": 4726254,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 1005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470902.757, "dur": 10.121, + "args": { + "External id": 4726255,"Record function id": 0, "Sequence number": 47018886, "Fwd thread id": 1, "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470903.949, "dur": 7.274, + "args": { + "External id": 4726256,"Sequence number": 47018886, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1007 + } + }, + { + "ph": "f", "id": 106, "pid": 1336753, "tid": 1381210, "ts": 1712359470903.949, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359470905.248, "dur": 5.808, + "args": { + "External id": 4726257,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470909.861, "dur": 1.062, + "args": { + "External id": 4726258,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470916.215, "dur": 6.819, + "args": { + "External id": 4726259,"Record function id": 0, "Sequence number": 47018885, "Fwd thread id": 1, "Ev Idx": 1010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470917.272, "dur": 3.779, + "args": { + "External id": 4726260,"Sequence number": 47018885, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1011 + } + }, + { + "ph": "f", "id": 107, "pid": 1336753, "tid": 1381210, "ts": 1712359470917.272, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359470918.146, "dur": 2.696, + "args": { + "External id": 4726261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359470918.770, "dur": 1.557, + "args": { + "External id": 4726262,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359470919.650, "dur": 0.555, + "args": { + "External id": 4726263,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359470926.720, "dur": 4.275, + "args": { + "External id": 4726264,"Record function id": 0, "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359470927.788, "dur": 2.674, + "args": { + "External id": 4726265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359470928.729, "dur": 1.433, + "args": { + "External id": 4726266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359470929.220, "dur": 0.852, + "args": { + "External id": 4726267,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470936.395, "dur": 9.158, + "args": { + "External id": 4726268,"Record function id": 0, "Sequence number": 47018884, "Fwd thread id": 1, "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470937.137, "dur": 5.885, + "args": { + "External id": 4726269,"Sequence number": 47018884, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 1020 + } + }, + { + "ph": "f", "id": 108, "pid": 1336753, "tid": 1381210, "ts": 1712359470937.137, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359470940.013, "dur": 2.861, + "args": { + "External id": 4726270,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359470942.148, "dur": 0.633, + "args": { + "External id": 4726271,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359470948.837, "dur": 267.371, + "args": { + "External id": 4726272,"Record function id": 0, "Sequence number": 47018883, "Fwd thread id": 1, "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471080.435, "dur": 125.466, + "args": { + "External id": 4726273,"Sequence number": 47018883, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1024 + } + }, + { + "ph": "f", "id": 109, "pid": 1336753, "tid": 1381210, "ts": 1712359471080.435, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359471086.692, "dur": 5.956, + "args": { + "External id": 4726274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359471087.551, "dur": 4.384, + "args": { + "External id": 4726275,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 1026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471090.876, "dur": 0.764, + "args": { + "External id": 4726276,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 1027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359471093.442, "dur": 46.496, + "args": { + "External id": 4726277,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 1028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359471141.219, "dur": 6.805, + "args": { + "External id": 4726278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359471141.711, "dur": 5.695, + "args": { + "External id": 4726279,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471142.598, "dur": 4.632, + "args": { + "External id": 4726280,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359471149.829, "dur": 6.455, + "args": { + "External id": 4726281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359471151.451, "dur": 4.390, + "args": { + "External id": 4726282,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471155.309, "dur": 0.434, + "args": { + "External id": 4726283,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359471156.771, "dur": 48.450, + "args": { + "External id": 4726284,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 1035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471222.999, "dur": 33.082, + "args": { + "External id": 4726285,"Record function id": 0, "Sequence number": 47018882, "Fwd thread id": 1, "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471224.140, "dur": 3.887, + "args": { + "External id": 4726286,"Sequence number": 47018882, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1037 + } + }, + { + "ph": "f", "id": 110, "pid": 1336753, "tid": 1381210, "ts": 1712359471224.140, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359471225.740, "dur": 2.140, + "args": { + "External id": 4726287,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471226.441, "dur": 1.339, + "args": { + "External id": 4726288,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1381210, + "ts": 1712359471231.368, "dur": 21.424, + "args": { + "External id": 4726289,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471260.017, "dur": 10.793, + "args": { + "External id": 4726290,"Record function id": 0, "Sequence number": 47018881, "Fwd thread id": 1, "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471260.899, "dur": 7.928, + "args": { + "External id": 4726291,"Sequence number": 47018881, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1042 + } + }, + { + "ph": "f", "id": 111, "pid": 1336753, "tid": 1381210, "ts": 1712359471260.899, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359471264.012, "dur": 4.610, + "args": { + "External id": 4726292,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359471264.705, "dur": 3.411, + "args": { + "External id": 4726293,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471267.446, "dur": 0.570, + "args": { + "External id": 4726294,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359471275.180, "dur": 5.444, + "args": { + "External id": 4726295,"Record function id": 0, "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359471276.415, "dur": 3.702, + "args": { + "External id": 4726296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359471277.666, "dur": 2.032, + "args": { + "External id": 4726297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359471278.284, "dur": 1.341, + "args": { + "External id": 4726298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359471284.710, "dur": 405.258, + "args": { + "External id": 4726299,"Record function id": 0, "Sequence number": 47018880, "Fwd thread id": 1, "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359471285.851, "dur": 372.008, + "args": { + "External id": 4726300,"Sequence number": 47018880, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 1051 + } + }, + { + "ph": "f", "id": 112, "pid": 1336753, "tid": 1381210, "ts": 1712359471285.851, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1712359471312.493, "dur": 30.250, + "args": { + "External id": 4726301,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359471313.959, "dur": 28.581, + "args": { + "External id": 4726302,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359471316.467, "dur": 5.821, + "args": { + "External id": 4726303,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 1054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359471318.762, "dur": 3.047, + "args": { + "External id": 4726304,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359471323.421, "dur": 18.750, + "args": { + "External id": 4726305,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359471358.260, "dur": 4.079, + "args": { + "External id": 4726306,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471358.767, "dur": 3.445, + "args": { + "External id": 4726307,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359471365.919, "dur": 1.192, + "args": { + "External id": 4726308,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471366.311, "dur": 0.708, + "args": { + "External id": 4726309,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359471380.969, "dur": 2.206, + "args": { + "External id": 4726310,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359471393.273, "dur": 2.436, + "args": { + "External id": 4726311,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471555.062, "dur": 2.040, + "args": { + "External id": 4726312,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 1063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359471562.487, "dur": 28.804, + "args": { + "External id": 4726313,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 1064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471570.542, "dur": 0.612, + "args": { + "External id": 4726314,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 1065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359471596.438, "dur": 29.295, + "args": { + "External id": 4726315,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 1066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359471598.023, "dur": 27.454, + "args": { + "External id": 4726316,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 1067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471603.466, "dur": 4.124, + "args": { + "External id": 4726317,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359471610.689, "dur": 14.192, + "args": { + "External id": 4726318,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 1069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359471629.709, "dur": 1.993, + "args": { + "External id": 4726319,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 1070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471630.545, "dur": 1.050, + "args": { + "External id": 4726320,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 1071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359471638.443, "dur": 4.510, + "args": { + "External id": 4726321,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471639.188, "dur": 3.651, + "args": { + "External id": 4726322,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359471644.714, "dur": 3.335, + "args": { + "External id": 4726323,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471646.876, "dur": 1.070, + "args": { + "External id": 4726324,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359471672.941, "dur": 15.483, + "args": { + "External id": 4726325,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359471699.088, "dur": 7.528, + "args": { + "External id": 4726326,"Record function id": 0, "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359471700.890, "dur": 5.143, + "args": { + "External id": 4726327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359471702.450, "dur": 2.757, + "args": { + "External id": 4726328,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359471703.420, "dur": 1.701, + "args": { + "External id": 4726329,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471710.232, "dur": 6.809, + "args": { + "External id": 4726330,"Record function id": 0, "Sequence number": 47018879, "Fwd thread id": 1, "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471711.008, "dur": 3.143, + "args": { + "External id": 4726331,"Sequence number": 47018879, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1082 + } + }, + { + "ph": "f", "id": 113, "pid": 1336753, "tid": 1381210, "ts": 1712359471711.008, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359471712.361, "dur": 1.625, + "args": { + "External id": 4726332,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471712.840, "dur": 1.003, + "args": { + "External id": 4726333,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471722.362, "dur": 112.775, + "args": { + "External id": 4726334,"Record function id": 0, "Sequence number": 47018878, "Fwd thread id": 1, "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471723.274, "dur": 105.658, + "args": { + "External id": 4726335,"Sequence number": 47018878, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1086 + } + }, + { + "ph": "f", "id": 114, "pid": 1336753, "tid": 1381210, "ts": 1712359471723.274, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359471726.689, "dur": 3.202, + "args": { + "External id": 4726336,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359471727.629, "dur": 1.777, + "args": { + "External id": 4726337,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471728.689, "dur": 0.533, + "args": { + "External id": 4726338,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359471730.894, "dur": 44.405, + "args": { + "External id": 4726339,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359471776.413, "dur": 9.137, + "args": { + "External id": 4726340,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359471779.032, "dur": 5.986, + "args": { + "External id": 4726341,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471781.899, "dur": 2.954, + "args": { + "External id": 4726342,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359471786.813, "dur": 3.516, + "args": { + "External id": 4726343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359471788.807, "dur": 1.153, + "args": { + "External id": 4726344,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471789.376, "dur": 0.469, + "args": { + "External id": 4726345,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359471790.829, "dur": 37.382, + "args": { + "External id": 4726346,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471839.637, "dur": 13.479, + "args": { + "External id": 4726347,"Record function id": 0, "Sequence number": 47018877, "Fwd thread id": 1, "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471840.894, "dur": 9.392, + "args": { + "External id": 4726348,"Sequence number": 47018877, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1099 + } + }, + { + "ph": "f", "id": 115, "pid": 1336753, "tid": 1381210, "ts": 1712359471840.894, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359471844.499, "dur": 5.645, + "args": { + "External id": 4726349,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471846.996, "dur": 3.048, + "args": { + "External id": 4726350,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471858.237, "dur": 6.243, + "args": { + "External id": 4726351,"Record function id": 0, "Sequence number": 47018876, "Fwd thread id": 1, "Ev Idx": 1102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471859.271, "dur": 3.696, + "args": { + "External id": 4726352,"Sequence number": 47018876, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1103 + } + }, + { + "ph": "f", "id": 116, "pid": 1336753, "tid": 1381210, "ts": 1712359471859.271, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359471860.100, "dur": 2.682, + "args": { + "External id": 4726353,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359471860.814, "dur": 1.475, + "args": { + "External id": 4726354,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471861.651, "dur": 0.491, + "args": { + "External id": 4726355,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359471868.442, "dur": 7.279, + "args": { + "External id": 4726356,"Record function id": 0, "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359471870.060, "dur": 5.178, + "args": { + "External id": 4726357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359471870.959, "dur": 3.916, + "args": { + "External id": 4726358,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359471873.803, "dur": 0.934, + "args": { + "External id": 4726359,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471880.948, "dur": 5.905, + "args": { + "External id": 4726360,"Record function id": 0, "Sequence number": 47018875, "Fwd thread id": 1, "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359471881.781, "dur": 2.968, + "args": { + "External id": 4726361,"Sequence number": 47018875, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1112 + } + }, + { + "ph": "f", "id": 117, "pid": 1336753, "tid": 1381210, "ts": 1712359471881.781, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359471882.997, "dur": 1.598, + "args": { + "External id": 4726362,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359471883.397, "dur": 1.056, + "args": { + "External id": 4726363,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359471892.465, "dur": 398.999, + "args": { + "External id": 4726364,"Record function id": 0, "Sequence number": 47018874, "Fwd thread id": 1, "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359471893.517, "dur": 371.547, + "args": { + "External id": 4726365,"Sequence number": 47018874, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1116 + } + }, + { + "ph": "f", "id": 118, "pid": 1336753, "tid": 1381210, "ts": 1712359471893.517, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359471910.829, "dur": 5.315, + "args": { + "External id": 4726366,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471912.904, "dur": 2.913, + "args": { + "External id": 4726367,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359471918.139, "dur": 6.438, + "args": { + "External id": 4726368,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471920.576, "dur": 3.786, + "args": { + "External id": 4726369,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359471962.597, "dur": 5.215, + "args": { + "External id": 4726370,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359471965.651, "dur": 1.910, + "args": { + "External id": 4726371,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359472033.414, "dur": 203.590, + "args": { + "External id": 4726372,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359472136.429, "dur": 6.586, + "args": { + "External id": 4726373,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359472144.902, "dur": 4.004, + "args": { + "External id": 4726374,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359472250.556, "dur": 4.608, + "args": { + "External id": 4726375,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359472258.208, "dur": 0.825, + "args": { + "External id": 4726376,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359472261.155, "dur": 0.827, + "args": { + "External id": 4726377,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359472301.861, "dur": 222.833, + "args": { + "External id": 4726378,"Record function id": 0, "Sequence number": 47018873, "Fwd thread id": 1, "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359472303.685, "dur": 213.117, + "args": { + "External id": 4726379,"Sequence number": 47018873, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1130 + } + }, + { + "ph": "f", "id": 119, "pid": 1336753, "tid": 1381210, "ts": 1712359472303.685, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359472323.970, "dur": 44.988, + "args": { + "External id": 4726380,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359472327.002, "dur": 3.291, + "args": { + "External id": 4726381,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359472331.946, "dur": 36.315, + "args": { + "External id": 4726382,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 1133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359472378.205, "dur": 5.993, + "args": { + "External id": 4726383,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359472381.351, "dur": 2.519, + "args": { + "External id": 4726384,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359472531.811, "dur": 166.492, + "args": { + "External id": 4726385,"Record function id": 0, "Sequence number": 47018872, "Fwd thread id": 1, "Ev Idx": 1136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359472533.425, "dur": 159.006, + "args": { + "External id": 4726386,"Sequence number": 47018872, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1137 + } + }, + { + "ph": "f", "id": 120, "pid": 1336753, "tid": 1381210, "ts": 1712359472533.425, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359472545.068, "dur": 48.266, + "args": { + "External id": 4726387,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359472547.127, "dur": 2.512, + "args": { + "External id": 4726388,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359472563.519, "dur": 29.394, + "args": { + "External id": 4726389,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 1140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359472601.062, "dur": 6.244, + "args": { + "External id": 4726390,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359472604.722, "dur": 2.273, + "args": { + "External id": 4726391,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472707.034, "dur": 16.220, + "args": { + "External id": 4726392,"Record function id": 0, "Sequence number": 47018871, "Fwd thread id": 1, "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472708.297, "dur": 11.784, + "args": { + "External id": 4726393,"Sequence number": 47018871, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1144 + } + }, + { + "ph": "f", "id": 121, "pid": 1336753, "tid": 1381210, "ts": 1712359472708.297, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359472710.832, "dur": 8.939, + "args": { + "External id": 4726394,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359472711.999, "dur": 7.557, + "args": { + "External id": 4726395,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472726.717, "dur": 8.382, + "args": { + "External id": 4726396,"Record function id": 0, "Sequence number": 47018870, "Fwd thread id": 1, "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472727.834, "dur": 5.410, + "args": { + "External id": 4726397,"Sequence number": 47018870, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1148 + } + }, + { + "ph": "f", "id": 122, "pid": 1336753, "tid": 1381210, "ts": 1712359472727.834, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359472729.192, "dur": 3.924, + "args": { + "External id": 4726398,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359472731.869, "dur": 1.130, + "args": { + "External id": 4726399,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472738.327, "dur": 9.099, + "args": { + "External id": 4726400,"Record function id": 0, "Sequence number": 47018869, "Fwd thread id": 1, "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472739.457, "dur": 5.364, + "args": { + "External id": 4726401,"Sequence number": 47018869, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1152 + } + }, + { + "ph": "f", "id": 123, "pid": 1336753, "tid": 1381210, "ts": 1712359472739.457, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359472742.672, "dur": 2.019, + "args": { + "External id": 4726402,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359472743.348, "dur": 1.211, + "args": { + "External id": 4726403,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472750.790, "dur": 7.951, + "args": { + "External id": 4726404,"Record function id": 0, "Sequence number": 47018868, "Fwd thread id": 1, "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472751.863, "dur": 4.512, + "args": { + "External id": 4726405,"Sequence number": 47018868, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1156 + } + }, + { + "ph": "f", "id": 124, "pid": 1336753, "tid": 1381210, "ts": 1712359472751.863, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359472753.025, "dur": 3.222, + "args": { + "External id": 4726406,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359472755.216, "dur": 0.944, + "args": { + "External id": 4726407,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472761.916, "dur": 144.781, + "args": { + "External id": 4726408,"Record function id": 0, "Sequence number": 47018867, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472762.730, "dur": 136.715, + "args": { + "External id": 4726409,"Sequence number": 47018867, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1160 + } + }, + { + "ph": "f", "id": 125, "pid": 1336753, "tid": 1381210, "ts": 1712359472762.730, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359472767.720, "dur": 8.836, + "args": { + "External id": 4726410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359472771.833, "dur": 4.049, + "args": { + "External id": 4726411,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359472774.058, "dur": 1.505, + "args": { + "External id": 4726412,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359472778.007, "dur": 62.913, + "args": { + "External id": 4726413,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359472842.095, "dur": 3.922, + "args": { + "External id": 4726414,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359472843.004, "dur": 2.388, + "args": { + "External id": 4726415,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359472844.127, "dur": 1.111, + "args": { + "External id": 4726416,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359472847.752, "dur": 7.716, + "args": { + "External id": 4726417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359472851.355, "dur": 3.500, + "args": { + "External id": 4726418,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359472854.152, "dur": 0.576, + "args": { + "External id": 4726419,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359472856.050, "dur": 42.619, + "args": { + "External id": 4726420,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472913.404, "dur": 6.707, + "args": { + "External id": 4726421,"Record function id": 0, "Sequence number": 47018866, "Fwd thread id": 1, "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472914.363, "dur": 3.893, + "args": { + "External id": 4726422,"Sequence number": 47018866, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1173 + } + }, + { + "ph": "f", "id": 126, "pid": 1336753, "tid": 1381210, "ts": 1712359472914.363, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359472915.987, "dur": 2.130, + "args": { + "External id": 4726423,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359472916.870, "dur": 1.146, + "args": { + "External id": 4726424,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472923.599, "dur": 8.566, + "args": { + "External id": 4726425,"Record function id": 0, "Sequence number": 47018865, "Fwd thread id": 1, "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472924.474, "dur": 5.666, + "args": { + "External id": 4726426,"Sequence number": 47018865, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1177 + } + }, + { + "ph": "f", "id": 127, "pid": 1336753, "tid": 1381210, "ts": 1712359472924.474, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359472927.330, "dur": 2.610, + "args": { + "External id": 4726427,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359472928.237, "dur": 1.252, + "args": { + "External id": 4726428,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359472929.024, "dur": 0.352, + "args": { + "External id": 4726429,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359472939.609, "dur": 9.113, + "args": { + "External id": 4726430,"Record function id": 0, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359472941.197, "dur": 6.829, + "args": { + "External id": 4726431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359472943.826, "dur": 3.855, + "args": { + "External id": 4726432,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359472945.013, "dur": 2.494, + "args": { + "External id": 4726433,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472952.086, "dur": 7.766, + "args": { + "External id": 4726434,"Record function id": 0, "Sequence number": 47018864, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472952.890, "dur": 4.741, + "args": { + "External id": 4726435,"Sequence number": 47018864, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1186 + } + }, + { + "ph": "f", "id": 128, "pid": 1336753, "tid": 1381210, "ts": 1712359472952.890, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359472954.357, "dur": 3.131, + "args": { + "External id": 4726436,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359472956.749, "dur": 0.614, + "args": { + "External id": 4726437,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472962.900, "dur": 159.164, + "args": { + "External id": 4726438,"Record function id": 0, "Sequence number": 47018863, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359472963.956, "dur": 150.074, + "args": { + "External id": 4726439,"Sequence number": 47018863, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1190 + } + }, + { + "ph": "f", "id": 129, "pid": 1336753, "tid": 1381210, "ts": 1712359472963.956, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359472966.972, "dur": 2.685, + "args": { + "External id": 4726440,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359472967.809, "dur": 1.452, + "args": { + "External id": 4726441,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359472968.634, "dur": 0.526, + "args": { + "External id": 4726442,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359472970.314, "dur": 68.341, + "args": { + "External id": 4726443,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359473042.534, "dur": 6.172, + "args": { + "External id": 4726444,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359473043.455, "dur": 4.455, + "args": { + "External id": 4726445,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473046.873, "dur": 0.893, + "args": { + "External id": 4726446,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359473050.190, "dur": 5.774, + "args": { + "External id": 4726447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359473051.793, "dur": 3.770, + "args": { + "External id": 4726448,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473052.576, "dur": 2.888, + "args": { + "External id": 4726449,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359473058.094, "dur": 54.879, + "args": { + "External id": 4726450,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473128.807, "dur": 34.093, + "args": { + "External id": 4726451,"Record function id": 0, "Sequence number": 47018862, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473130.253, "dur": 5.919, + "args": { + "External id": 4726452,"Sequence number": 47018862, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1203 + } + }, + { + "ph": "f", "id": 130, "pid": 1336753, "tid": 1381210, "ts": 1712359473130.253, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359473132.072, "dur": 3.968, + "args": { + "External id": 4726453,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359473134.456, "dur": 1.500, + "args": { + "External id": 4726454,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1381210, + "ts": 1712359473139.147, "dur": 21.422, + "args": { + "External id": 4726455,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473168.780, "dur": 9.799, + "args": { + "External id": 4726456,"Record function id": 0, "Sequence number": 47018861, "Fwd thread id": 1, "Ev Idx": 1207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473169.723, "dur": 6.950, + "args": { + "External id": 4726457,"Sequence number": 47018861, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1208 + } + }, + { + "ph": "f", "id": 131, "pid": 1336753, "tid": 1381210, "ts": 1712359473169.723, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359473170.917, "dur": 5.557, + "args": { + "External id": 4726458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359473173.729, "dur": 2.158, + "args": { + "External id": 4726459,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473175.080, "dur": 0.713, + "args": { + "External id": 4726460,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359473182.652, "dur": 6.991, + "args": { + "External id": 4726461,"Record function id": 0, "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359473183.851, "dur": 5.155, + "args": { + "External id": 4726462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359473185.796, "dur": 2.422, + "args": { + "External id": 4726463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359473186.570, "dur": 1.548, + "args": { + "External id": 4726464,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473192.778, "dur": 12.124, + "args": { + "External id": 4726465,"Record function id": 0, "Sequence number": 47018860, "Fwd thread id": 1, "Ev Idx": 1216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473194.339, "dur": 7.683, + "args": { + "External id": 4726466,"Sequence number": 47018860, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1217 + } + }, + { + "ph": "f", "id": 132, "pid": 1336753, "tid": 1381210, "ts": 1712359473194.339, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359473195.671, "dur": 6.205, + "args": { + "External id": 4726467,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359473200.847, "dur": 0.937, + "args": { + "External id": 4726468,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473210.070, "dur": 90.773, + "args": { + "External id": 4726469,"Record function id": 0, "Sequence number": 47018859, "Fwd thread id": 1, "Ev Idx": 1220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473211.311, "dur": 81.186, + "args": { + "External id": 4726470,"Sequence number": 47018859, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1221 + } + }, + { + "ph": "f", "id": 133, "pid": 1336753, "tid": 1381210, "ts": 1712359473211.311, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359473214.153, "dur": 2.306, + "args": { + "External id": 4726471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359473214.978, "dur": 1.067, + "args": { + "External id": 4726472,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473215.569, "dur": 0.373, + "args": { + "External id": 4726473,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359473217.380, "dur": 28.217, + "args": { + "External id": 4726474,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359473246.687, "dur": 6.437, + "args": { + "External id": 4726475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359473249.004, "dur": 3.591, + "args": { + "External id": 4726476,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473250.135, "dur": 2.298, + "args": { + "External id": 4726477,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359473254.260, "dur": 5.345, + "args": { + "External id": 4726478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359473255.884, "dur": 3.336, + "args": { + "External id": 4726479,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473258.523, "dur": 0.634, + "args": { + "External id": 4726480,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359473260.135, "dur": 31.817, + "args": { + "External id": 4726481,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473304.815, "dur": 29.194, + "args": { + "External id": 4726482,"Record function id": 0, "Sequence number": 47018858, "Fwd thread id": 1, "Ev Idx": 1233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473305.950, "dur": 5.947, + "args": { + "External id": 4726483,"Sequence number": 47018858, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1234 + } + }, + { + "ph": "f", "id": 134, "pid": 1336753, "tid": 1381210, "ts": 1712359473305.950, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359473309.437, "dur": 2.318, + "args": { + "External id": 4726484,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359473310.703, "dur": 0.967, + "args": { + "External id": 4726485,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359473314.121, "dur": 17.825, + "args": { + "External id": 4726486,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473337.463, "dur": 8.614, + "args": { + "External id": 4726487,"Record function id": 0, "Sequence number": 47018857, "Fwd thread id": 1, "Ev Idx": 1238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473338.657, "dur": 4.224, + "args": { + "External id": 4726488,"Sequence number": 47018857, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1239 + } + }, + { + "ph": "f", "id": 135, "pid": 1336753, "tid": 1381210, "ts": 1712359473338.657, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359473339.674, "dur": 3.014, + "args": { + "External id": 4726489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359473340.422, "dur": 1.800, + "args": { + "External id": 4726490,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473341.414, "dur": 0.645, + "args": { + "External id": 4726491,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359473351.343, "dur": 6.865, + "args": { + "External id": 4726492,"Record function id": 0, "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359473352.875, "dur": 4.860, + "args": { + "External id": 4726493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359473353.745, "dur": 3.586, + "args": { + "External id": 4726494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359473356.088, "dur": 1.140, + "args": { + "External id": 4726495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359473363.742, "dur": 337.333, + "args": { + "External id": 4726496,"Record function id": 0, "Sequence number": 47018856, "Fwd thread id": 1, "Ev Idx": 1247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359473364.658, "dur": 307.548, + "args": { + "External id": 4726497,"Sequence number": 47018856, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1248 + } + }, + { + "ph": "f", "id": 136, "pid": 1336753, "tid": 1381210, "ts": 1712359473364.658, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359473396.241, "dur": 1.858, + "args": { + "External id": 4726498,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359473397.049, "dur": 0.937, + "args": { + "External id": 4726499,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359473411.587, "dur": 6.386, + "args": { + "External id": 4726500,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359473426.463, "dur": 1.699, + "args": { + "External id": 4726501,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359473574.567, "dur": 1.638, + "args": { + "External id": 4726502,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 1253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359473579.980, "dur": 32.272, + "args": { + "External id": 4726503,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 1254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473589.237, "dur": 1.016, + "args": { + "External id": 4726504,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 1255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359473617.500, "dur": 30.634, + "args": { + "External id": 4726505,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 1256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359473619.478, "dur": 28.339, + "args": { + "External id": 4726506,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 1257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473624.752, "dur": 6.202, + "args": { + "External id": 4726507,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359473632.122, "dur": 15.216, + "args": { + "External id": 4726508,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 1259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359473652.003, "dur": 4.598, + "args": { + "External id": 4726509,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 1260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359473655.211, "dur": 1.282, + "args": { + "External id": 4726510,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 1261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359473663.477, "dur": 1.972, + "args": { + "External id": 4726511,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359473664.371, "dur": 0.997, + "args": { + "External id": 4726512,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359473682.729, "dur": 13.926, + "args": { + "External id": 4726513,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359473711.236, "dur": 8.003, + "args": { + "External id": 4726514,"Record function id": 0, "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359473713.026, "dur": 5.426, + "args": { + "External id": 4726515,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359473714.736, "dur": 2.661, + "args": { + "External id": 4726516,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359473715.715, "dur": 1.575, + "args": { + "External id": 4726517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473723.096, "dur": 9.387, + "args": { + "External id": 4726518,"Record function id": 0, "Sequence number": 47018855, "Fwd thread id": 1, "Ev Idx": 1269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359473726.316, "dur": 1.516, + "args": { + "External id": 4726519,"Sequence number": 47018855, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1270 + } + }, + { + "ph": "f", "id": 137, "pid": 1336753, "tid": 1381210, "ts": 1712359473726.316, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359473736.540, "dur": 479.732, + "args": { + "External id": 4726520,"Record function id": 0, "Sequence number": 47018854, "Fwd thread id": 1, "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359473739.765, "dur": 462.068, + "args": { + "External id": 4726521,"Sequence number": 47018854, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1272 + } + }, + { + "ph": "f", "id": 138, "pid": 1336753, "tid": 1381210, "ts": 1712359473739.765, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359473768.668, "dur": 7.582, + "args": { + "External id": 4726522,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359473773.059, "dur": 2.900, + "args": { + "External id": 4726523,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]", "[8192, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[33554432, 8192, 1], [], []], "Input Dims": [[16, 4096, 2048], [], []], "Ev Idx": 1274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359473779.539, "dur": 8.534, + "args": { + "External id": 4726524,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359473780.743, "dur": 6.771, + "args": { + "External id": 4726525,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473784.394, "dur": 2.918, + "args": { + "External id": 4726526,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1381210, + "ts": 1712359473791.326, "dur": 78.557, + "args": { + "External id": 4726527,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8192, 1], [1, 5632], []], "Input Dims": [[65536, 2048], [5632, 2048], []], "Ev Idx": 1278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359473792.357, "dur": 4.956, + "args": { + "External id": 4726528,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 5632]], "Input Dims": [[5632, 2048]], "Ev Idx": 1279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359473793.184, "dur": 3.709, + "args": { + "External id": 4726529,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 5632], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473796.193, "dur": 0.607, + "args": { + "External id": 4726530,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[5632, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 5632], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1381210, + "ts": 1712359473798.476, "dur": 70.926, + "args": { + "External id": 4726531,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 1282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359473799.756, "dur": 68.940, + "args": { + "External id": 4726532,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 1283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359473874.047, "dur": 2.233, + "args": { + "External id": 4726533,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [23068672, 5632, 1]], "Input Dims": [[65536, 5632], [16, 4096, 5632]], "Ev Idx": 1284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359473875.033, "dur": 1.145, + "args": { + "External id": 4726534,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 1285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359473905.639, "dur": 5.077, + "args": { + "External id": 4726535,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359473913.999, "dur": 2.204, + "args": { + "External id": 4726536,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359473916.945, "dur": 2.070, + "args": { + "External id": 4726537,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359473949.768, "dur": 1.756, + "args": { + "External id": 4726538,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359473950.286, "dur": 1.064, + "args": { + "External id": 4726539,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 1336753, "tid": 1381210, + "ts": 1712359473973.079, "dur": 204.620, + "args": { + "External id": 4726540,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[8192, 1], [5632, 1]], []], "Input Dims": [[], [[65536, 2048], [65536, 5632]], []], "Ev Idx": 1291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1381210, + "ts": 1712359473977.759, "dur": 57.892, + "args": { + "External id": 4726541,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359473982.430, "dur": 51.453, + "args": { + "External id": 4726542,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048, 1]", "[8192, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359474037.957, "dur": 6.025, + "args": { + "External id": 4726543,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8192, 1, 1], []], "Input Dims": [[65536, 2048, 1], []], "Ev Idx": 1294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474042.790, "dur": 0.572, + "args": { + "External id": 4726544,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 65536]", "[1, 1, 8192]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[65536, 2048, 1], [], [], []], "Ev Idx": 1295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1381210, + "ts": 1712359474045.757, "dur": 1.623, + "args": { + "External id": 4726545,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 1296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474046.719, "dur": 0.319, + "args": { + "External id": 4726546,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 1297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359474049.754, "dur": 1.872, + "args": { + "External id": 4726547,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 1298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474050.517, "dur": 0.484, + "args": { + "External id": 4726548,"Record function id": 0, "Concrete Inputs": ["", "[1, 5632, 65536]", "[1, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1, 1], [], [], []], "Input Dims": [[65536, 5632, 1], [], [], []], "Ev Idx": 1299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359474057.161, "dur": 3.905, + "args": { + "External id": 4726549,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 8192], []], "Input Dims": [[2048, 1, 65536], []], "Ev Idx": 1300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474060.037, "dur": 0.760, + "args": { + "External id": 4726550,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536, 1]", "[1, 8192, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 8192], [], [], []], "Input Dims": [[2048, 1, 65536], [], [], []], "Ev Idx": 1301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359474061.841, "dur": 28.261, + "args": { + "External id": 4726551,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 8192, 1], []], "Input Dims": [[2048, 65536, 1], []], "Ev Idx": 1302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359474087.327, "dur": 2.506, + "args": { + "External id": 4726552,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]", "[2048, 1, 8192]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 8192, 1], [], []], "Input Dims": [[2048, 65536, 1], [], []], "Ev Idx": 1303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359474090.903, "dur": 3.949, + "args": { + "External id": 4726553,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 5632], []], "Input Dims": [[1, 5632, 65536], []], "Ev Idx": 1304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474093.934, "dur": 0.640, + "args": { + "External id": 4726554,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 5632], [], [], []], "Input Dims": [[1, 5632, 65536], [], [], []], "Ev Idx": 1305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359474095.310, "dur": 3.713, + "args": { + "External id": 4726555,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 1306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474096.001, "dur": 2.922, + "args": { + "External id": 4726556,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 1307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359474100.202, "dur": 63.630, + "args": { + "External id": 4726557,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1, 8192], [369098752, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632]], "Ev Idx": 1308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474166.930, "dur": 1.324, + "args": { + "External id": 4726558,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 5632, 1], []], "Input Dims": [[1, 2048, 5632], []], "Ev Idx": 1309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336753, "tid": 1381210, + "ts": 1712359474168.884, "dur": 2.254, + "args": { + "External id": 4726559,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 5632, 1], []], "Input Dims": [[2048, 1, 5632], []], "Ev Idx": 1310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474170.039, "dur": 0.522, + "args": { + "External id": 4726560,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632, 1]", "[5632, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 5632, 1], [], [], []], "Input Dims": [[2048, 1, 5632], [], [], []], "Ev Idx": 1311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474175.467, "dur": 1.044, + "args": { + "External id": 4726561,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 5632], []], "Input Dims": [[2048, 5632, 1], []], "Ev Idx": 1312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359474232.851, "dur": 9.504, + "args": { + "External id": 4726562,"Record function id": 0, "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359474235.177, "dur": 6.454, + "args": { + "External id": 4726563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359474237.411, "dur": 3.402, + "args": { + "External id": 4726564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359474238.740, "dur": 1.984, + "args": { + "External id": 4726565,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474245.980, "dur": 7.504, + "args": { + "External id": 4726566,"Record function id": 0, "Sequence number": 47018853, "Fwd thread id": 1, "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474247.060, "dur": 4.164, + "args": { + "External id": 4726567,"Sequence number": 47018853, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 1318 + } + }, + { + "ph": "f", "id": 139, "pid": 1336753, "tid": 1381210, "ts": 1712359474247.060, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359474248.791, "dur": 2.211, + "args": { + "External id": 4726568,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474249.902, "dur": 0.964, + "args": { + "External id": 4726569,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474257.060, "dur": 127.405, + "args": { + "External id": 4726570,"Record function id": 0, "Sequence number": 47018852, "Fwd thread id": 1, "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474258.343, "dur": 119.084, + "args": { + "External id": 4726571,"Sequence number": 47018852, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1322 + } + }, + { + "ph": "f", "id": 140, "pid": 1336753, "tid": 1381210, "ts": 1712359474258.343, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359474264.963, "dur": 3.988, + "args": { + "External id": 4726572,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359474266.396, "dur": 1.970, + "args": { + "External id": 4726573,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 1324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474267.495, "dur": 0.669, + "args": { + "External id": 4726574,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 1325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359474270.149, "dur": 42.237, + "args": { + "External id": 4726575,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 1326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359474313.609, "dur": 7.854, + "args": { + "External id": 4726576,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359474314.493, "dur": 6.104, + "args": { + "External id": 4726577,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474319.568, "dur": 0.871, + "args": { + "External id": 4726578,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359474322.980, "dur": 5.630, + "args": { + "External id": 4726579,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359474324.827, "dur": 3.253, + "args": { + "External id": 4726580,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474325.933, "dur": 2.022, + "args": { + "External id": 4726581,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359474329.119, "dur": 47.478, + "args": { + "External id": 4726582,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 1333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474388.828, "dur": 7.313, + "args": { + "External id": 4726583,"Record function id": 0, "Sequence number": 47018851, "Fwd thread id": 1, "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474389.788, "dur": 5.102, + "args": { + "External id": 4726584,"Sequence number": 47018851, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1335 + } + }, + { + "ph": "f", "id": 141, "pid": 1336753, "tid": 1381210, "ts": 1712359474389.788, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359474390.992, "dur": 3.751, + "args": { + "External id": 4726585,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474393.599, "dur": 0.996, + "args": { + "External id": 4726586,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474399.659, "dur": 9.319, + "args": { + "External id": 4726587,"Record function id": 0, "Sequence number": 47018850, "Fwd thread id": 1, "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474400.648, "dur": 5.720, + "args": { + "External id": 4726588,"Sequence number": 47018850, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1339 + } + }, + { + "ph": "f", "id": 142, "pid": 1336753, "tid": 1381210, "ts": 1712359474400.648, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359474401.851, "dur": 4.302, + "args": { + "External id": 4726589,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359474402.355, "dur": 3.319, + "args": { + "External id": 4726590,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474405.081, "dur": 0.444, + "args": { + "External id": 4726591,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359474412.838, "dur": 4.998, + "args": { + "External id": 4726592,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359474413.959, "dur": 3.397, + "args": { + "External id": 4726593,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359474415.145, "dur": 1.935, + "args": { + "External id": 4726594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359474415.975, "dur": 1.039, + "args": { + "External id": 4726595,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474421.062, "dur": 8.058, + "args": { + "External id": 4726596,"Record function id": 0, "Sequence number": 47018849, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474422.015, "dur": 4.640, + "args": { + "External id": 4726597,"Sequence number": 47018849, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 1348 + } + }, + { + "ph": "f", "id": 143, "pid": 1336753, "tid": 1381210, "ts": 1712359474422.015, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359474425.001, "dur": 1.505, + "args": { + "External id": 4726598,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474425.550, "dur": 0.826, + "args": { + "External id": 4726599,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474432.213, "dur": 114.694, + "args": { + "External id": 4726600,"Record function id": 0, "Sequence number": 47018848, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474433.314, "dur": 106.586, + "args": { + "External id": 4726601,"Sequence number": 47018848, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1352 + } + }, + { + "ph": "f", "id": 144, "pid": 1336753, "tid": 1381210, "ts": 1712359474433.314, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359474435.815, "dur": 5.620, + "args": { + "External id": 4726602,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359474436.206, "dur": 4.840, + "args": { + "External id": 4726603,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 1354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474440.581, "dur": 0.370, + "args": { + "External id": 4726604,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 1355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359474442.021, "dur": 32.136, + "args": { + "External id": 4726605,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 1356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359474475.152, "dur": 5.288, + "args": { + "External id": 4726606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359474475.854, "dur": 3.977, + "args": { + "External id": 4726607,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474476.666, "dur": 3.009, + "args": { + "External id": 4726608,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359474481.438, "dur": 4.841, + "args": { + "External id": 4726609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359474482.740, "dur": 3.084, + "args": { + "External id": 4726610,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474485.182, "dur": 0.538, + "args": { + "External id": 4726611,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359474486.843, "dur": 52.271, + "args": { + "External id": 4726612,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 1363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474553.124, "dur": 32.003, + "args": { + "External id": 4726613,"Record function id": 0, "Sequence number": 47018847, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474553.964, "dur": 4.866, + "args": { + "External id": 4726614,"Sequence number": 47018847, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1365 + } + }, + { + "ph": "f", "id": 145, "pid": 1336753, "tid": 1381210, "ts": 1712359474553.964, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359474556.918, "dur": 1.758, + "args": { + "External id": 4726615,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474557.477, "dur": 1.054, + "args": { + "External id": 4726616,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1381210, + "ts": 1712359474561.414, "dur": 20.439, + "args": { + "External id": 4726617,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474588.747, "dur": 9.163, + "args": { + "External id": 4726618,"Record function id": 0, "Sequence number": 47018846, "Fwd thread id": 1, "Ev Idx": 1369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359474589.857, "dur": 5.775, + "args": { + "External id": 4726619,"Sequence number": 47018846, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1370 + } + }, + { + "ph": "f", "id": 146, "pid": 1336753, "tid": 1381210, "ts": 1712359474589.857, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359474590.770, "dur": 4.645, + "args": { + "External id": 4726620,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359474593.413, "dur": 1.534, + "args": { + "External id": 4726621,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474594.162, "dur": 0.633, + "args": { + "External id": 4726622,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359474601.946, "dur": 7.280, + "args": { + "External id": 4726623,"Record function id": 0, "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359474605.443, "dur": 3.305, + "args": { + "External id": 4726624,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359474606.385, "dur": 2.003, + "args": { + "External id": 4726625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359474606.878, "dur": 1.443, + "args": { + "External id": 4726626,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359474613.482, "dur": 486.038, + "args": { + "External id": 4726627,"Record function id": 0, "Sequence number": 47018845, "Fwd thread id": 1, "Ev Idx": 1378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359474629.589, "dur": 412.069, + "args": { + "External id": 4726628,"Sequence number": 47018845, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 1379 + } + }, + { + "ph": "f", "id": 147, "pid": 1336753, "tid": 1381210, "ts": 1712359474629.589, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1712359474654.609, "dur": 32.215, + "args": { + "External id": 4726629,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359474655.984, "dur": 30.641, + "args": { + "External id": 4726630,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359474658.652, "dur": 6.416, + "args": { + "External id": 4726631,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 1382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359474661.135, "dur": 3.430, + "args": { + "External id": 4726632,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359474666.363, "dur": 19.896, + "args": { + "External id": 4726633,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359474700.173, "dur": 5.791, + "args": { + "External id": 4726634,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474702.755, "dur": 3.061, + "args": { + "External id": 4726635,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359474709.726, "dur": 1.413, + "args": { + "External id": 4726636,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474710.239, "dur": 0.777, + "args": { + "External id": 4726637,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359474724.911, "dur": 2.616, + "args": { + "External id": 4726638,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359474738.206, "dur": 3.877, + "args": { + "External id": 4726639,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474891.909, "dur": 3.693, + "args": { + "External id": 4726640,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 1391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359474899.653, "dur": 30.561, + "args": { + "External id": 4726641,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 1392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474909.266, "dur": 0.818, + "args": { + "External id": 4726642,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 1393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359474935.437, "dur": 27.178, + "args": { + "External id": 4726643,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 1394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359474937.431, "dur": 24.961, + "args": { + "External id": 4726644,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 1395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359474940.777, "dur": 3.996, + "args": { + "External id": 4726645,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359474947.976, "dur": 13.775, + "args": { + "External id": 4726646,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 1397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359474967.152, "dur": 4.616, + "args": { + "External id": 4726647,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 1398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474970.528, "dur": 1.113, + "args": { + "External id": 4726648,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 1399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359474978.531, "dur": 4.005, + "args": { + "External id": 4726649,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359474979.248, "dur": 3.173, + "args": { + "External id": 4726650,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359475023.836, "dur": 4.665, + "args": { + "External id": 4726651,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359475026.372, "dur": 1.900, + "args": { + "External id": 4726652,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359475060.449, "dur": 36.625, + "args": { + "External id": 4726653,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359475114.287, "dur": 9.861, + "args": { + "External id": 4726654,"Record function id": 0, "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359475116.921, "dur": 6.371, + "args": { + "External id": 4726655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359475119.203, "dur": 3.289, + "args": { + "External id": 4726656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359475120.166, "dur": 2.231, + "args": { + "External id": 4726657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475127.589, "dur": 11.571, + "args": { + "External id": 4726658,"Record function id": 0, "Sequence number": 47018844, "Fwd thread id": 1, "Ev Idx": 1409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475129.047, "dur": 6.935, + "args": { + "External id": 4726659,"Sequence number": 47018844, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1410 + } + }, + { + "ph": "f", "id": 148, "pid": 1336753, "tid": 1381210, "ts": 1712359475129.047, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359475131.254, "dur": 4.493, + "args": { + "External id": 4726660,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359475134.057, "dur": 1.567, + "args": { + "External id": 4726661,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475142.726, "dur": 134.025, + "args": { + "External id": 4726662,"Record function id": 0, "Sequence number": 47018843, "Fwd thread id": 1, "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475144.262, "dur": 124.691, + "args": { + "External id": 4726663,"Sequence number": 47018843, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1414 + } + }, + { + "ph": "f", "id": 149, "pid": 1336753, "tid": 1381210, "ts": 1712359475144.262, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359475149.119, "dur": 4.677, + "args": { + "External id": 4726664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359475150.696, "dur": 2.480, + "args": { + "External id": 4726665,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475152.142, "dur": 0.763, + "args": { + "External id": 4726666,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359475155.087, "dur": 55.808, + "args": { + "External id": 4726667,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359475213.968, "dur": 6.839, + "args": { + "External id": 4726668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359475214.736, "dur": 5.406, + "args": { + "External id": 4726669,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475217.882, "dur": 2.082, + "args": { + "External id": 4726670,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359475222.422, "dur": 3.263, + "args": { + "External id": 4726671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359475224.004, "dur": 1.125, + "args": { + "External id": 4726672,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475224.562, "dur": 0.446, + "args": { + "External id": 4726673,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359475228.461, "dur": 39.710, + "args": { + "External id": 4726674,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475281.513, "dur": 11.564, + "args": { + "External id": 4726675,"Record function id": 0, "Sequence number": 47018842, "Fwd thread id": 1, "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475282.518, "dur": 8.104, + "args": { + "External id": 4726676,"Sequence number": 47018842, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1427 + } + }, + { + "ph": "f", "id": 150, "pid": 1336753, "tid": 1381210, "ts": 1712359475282.518, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359475284.297, "dur": 6.169, + "args": { + "External id": 4726677,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359475287.232, "dur": 3.089, + "args": { + "External id": 4726678,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475296.226, "dur": 9.159, + "args": { + "External id": 4726679,"Record function id": 0, "Sequence number": 47018841, "Fwd thread id": 1, "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475297.339, "dur": 6.134, + "args": { + "External id": 4726680,"Sequence number": 47018841, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1431 + } + }, + { + "ph": "f", "id": 151, "pid": 1336753, "tid": 1381210, "ts": 1712359475297.339, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359475298.292, "dur": 4.966, + "args": { + "External id": 4726681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359475298.990, "dur": 3.789, + "args": { + "External id": 4726682,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475302.169, "dur": 0.513, + "args": { + "External id": 4726683,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359475309.402, "dur": 5.045, + "args": { + "External id": 4726684,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359475310.371, "dur": 3.534, + "args": { + "External id": 4726685,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359475311.853, "dur": 1.753, + "args": { + "External id": 4726686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359475312.346, "dur": 1.170, + "args": { + "External id": 4726687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475317.751, "dur": 6.464, + "args": { + "External id": 4726688,"Record function id": 0, "Sequence number": 47018840, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359475318.793, "dur": 3.517, + "args": { + "External id": 4726689,"Sequence number": 47018840, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1440 + } + }, + { + "ph": "f", "id": 152, "pid": 1336753, "tid": 1381210, "ts": 1712359475318.793, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359475320.446, "dur": 1.723, + "args": { + "External id": 4726690,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359475320.949, "dur": 1.098, + "args": { + "External id": 4726691,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359475328.216, "dur": 288.957, + "args": { + "External id": 4726692,"Record function id": 0, "Sequence number": 47018839, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359475331.259, "dur": 263.757, + "args": { + "External id": 4726693,"Sequence number": 47018839, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1444 + } + }, + { + "ph": "f", "id": 153, "pid": 1336753, "tid": 1381210, "ts": 1712359475331.259, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359475348.285, "dur": 8.492, + "args": { + "External id": 4726694,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475352.542, "dur": 3.796, + "args": { + "External id": 4726695,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359475358.803, "dur": 5.354, + "args": { + "External id": 4726696,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475361.564, "dur": 2.398, + "args": { + "External id": 4726697,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359475365.579, "dur": 3.034, + "args": { + "External id": 4726698,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475366.674, "dur": 1.759, + "args": { + "External id": 4726699,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359475392.387, "dur": 178.199, + "args": { + "External id": 4726700,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359475471.565, "dur": 5.267, + "args": { + "External id": 4726701,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359475480.621, "dur": 3.885, + "args": { + "External id": 4726702,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359475582.718, "dur": 3.659, + "args": { + "External id": 4726703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359475589.367, "dur": 0.653, + "args": { + "External id": 4726704,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1381210, + "ts": 1712359475591.944, "dur": 0.811, + "args": { + "External id": 4726705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359475623.940, "dur": 220.919, + "args": { + "External id": 4726706,"Record function id": 0, "Sequence number": 47018838, "Fwd thread id": 1, "Ev Idx": 1457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359475625.355, "dur": 212.959, + "args": { + "External id": 4726707,"Sequence number": 47018838, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1458 + } + }, + { + "ph": "f", "id": 154, "pid": 1336753, "tid": 1381210, "ts": 1712359475625.355, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359475645.492, "dur": 53.203, + "args": { + "External id": 4726708,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475649.835, "dur": 2.849, + "args": { + "External id": 4726709,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359475654.240, "dur": 43.755, + "args": { + "External id": 4726710,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 1461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359475707.173, "dur": 4.289, + "args": { + "External id": 4726711,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475708.572, "dur": 2.487, + "args": { + "External id": 4726712,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359475851.136, "dur": 196.687, + "args": { + "External id": 4726713,"Record function id": 0, "Sequence number": 47018837, "Fwd thread id": 1, "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359475854.961, "dur": 183.776, + "args": { + "External id": 4726714,"Sequence number": 47018837, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1465 + } + }, + { + "ph": "f", "id": 155, "pid": 1336753, "tid": 1381210, "ts": 1712359475854.961, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1712359475867.280, "dur": 29.247, + "args": { + "External id": 4726715,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475869.213, "dur": 2.290, + "args": { + "External id": 4726716,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359475872.656, "dur": 23.383, + "args": { + "External id": 4726717,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 1468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1712359475902.917, "dur": 3.938, + "args": { + "External id": 4726718,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359475904.067, "dur": 2.428, + "args": { + "External id": 4726719,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476056.810, "dur": 35.885, + "args": { + "External id": 4726720,"Record function id": 0, "Sequence number": 47018836, "Fwd thread id": 1, "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476058.644, "dur": 29.601, + "args": { + "External id": 4726721,"Sequence number": 47018836, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1472 + } + }, + { + "ph": "f", "id": 156, "pid": 1336753, "tid": 1381210, "ts": 1712359476058.644, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476063.333, "dur": 24.620, + "args": { + "External id": 4726722,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476081.076, "dur": 6.557, + "args": { + "External id": 4726723,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476098.102, "dur": 7.754, + "args": { + "External id": 4726724,"Record function id": 0, "Sequence number": 47018835, "Fwd thread id": 1, "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476099.526, "dur": 4.055, + "args": { + "External id": 4726725,"Sequence number": 47018835, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1476 + } + }, + { + "ph": "f", "id": 157, "pid": 1336753, "tid": 1381210, "ts": 1712359476099.526, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476101.157, "dur": 2.278, + "args": { + "External id": 4726726,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476102.241, "dur": 1.089, + "args": { + "External id": 4726727,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476109.123, "dur": 9.267, + "args": { + "External id": 4726728,"Record function id": 0, "Sequence number": 47018834, "Fwd thread id": 1, "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476110.384, "dur": 6.140, + "args": { + "External id": 4726729,"Sequence number": 47018834, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1480 + } + }, + { + "ph": "f", "id": 158, "pid": 1336753, "tid": 1381210, "ts": 1712359476110.384, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476114.724, "dur": 1.659, + "args": { + "External id": 4726730,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476115.294, "dur": 1.005, + "args": { + "External id": 4726731,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476121.813, "dur": 6.623, + "args": { + "External id": 4726732,"Record function id": 0, "Sequence number": 47018833, "Fwd thread id": 1, "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476122.774, "dur": 3.166, + "args": { + "External id": 4726733,"Sequence number": 47018833, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1484 + } + }, + { + "ph": "f", "id": 159, "pid": 1336753, "tid": 1381210, "ts": 1712359476122.774, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476123.968, "dur": 1.814, + "args": { + "External id": 4726734,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476124.804, "dur": 0.844, + "args": { + "External id": 4726735,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476131.876, "dur": 149.474, + "args": { + "External id": 4726736,"Record function id": 0, "Sequence number": 47018832, "Fwd thread id": 1, "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476132.944, "dur": 140.432, + "args": { + "External id": 4726737,"Sequence number": 47018832, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1488 + } + }, + { + "ph": "f", "id": 160, "pid": 1336753, "tid": 1381210, "ts": 1712359476132.944, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476138.506, "dur": 10.288, + "args": { + "External id": 4726738,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476142.203, "dur": 6.016, + "args": { + "External id": 4726739,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476145.950, "dur": 2.016, + "args": { + "External id": 4726740,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359476150.237, "dur": 65.504, + "args": { + "External id": 4726741,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476216.979, "dur": 4.754, + "args": { + "External id": 4726742,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476217.894, "dur": 3.196, + "args": { + "External id": 4726743,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476219.690, "dur": 1.223, + "args": { + "External id": 4726744,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476223.436, "dur": 5.471, + "args": { + "External id": 4726745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476226.716, "dur": 1.753, + "args": { + "External id": 4726746,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476227.862, "dur": 0.539, + "args": { + "External id": 4726747,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359476229.898, "dur": 42.632, + "args": { + "External id": 4726748,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476285.904, "dur": 9.176, + "args": { + "External id": 4726749,"Record function id": 0, "Sequence number": 47018831, "Fwd thread id": 1, "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476287.101, "dur": 5.363, + "args": { + "External id": 4726750,"Sequence number": 47018831, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1501 + } + }, + { + "ph": "f", "id": 161, "pid": 1336753, "tid": 1381210, "ts": 1712359476287.101, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476290.338, "dur": 1.986, + "args": { + "External id": 4726751,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476291.058, "dur": 1.135, + "args": { + "External id": 4726752,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476298.172, "dur": 8.571, + "args": { + "External id": 4726753,"Record function id": 0, "Sequence number": 47018830, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476298.867, "dur": 5.323, + "args": { + "External id": 4726754,"Sequence number": 47018830, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1505 + } + }, + { + "ph": "f", "id": 162, "pid": 1336753, "tid": 1381210, "ts": 1712359476298.867, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476301.667, "dur": 2.335, + "args": { + "External id": 4726755,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476302.340, "dur": 1.111, + "args": { + "External id": 4726756,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476302.978, "dur": 0.390, + "args": { + "External id": 4726757,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359476312.549, "dur": 9.046, + "args": { + "External id": 4726758,"Record function id": 0, "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359476314.180, "dur": 6.708, + "args": { + "External id": 4726759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359476316.688, "dur": 3.644, + "args": { + "External id": 4726760,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359476317.995, "dur": 2.240, + "args": { + "External id": 4726761,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476324.901, "dur": 10.429, + "args": { + "External id": 4726762,"Record function id": 0, "Sequence number": 47018829, "Fwd thread id": 1, "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476327.793, "dur": 5.024, + "args": { + "External id": 4726763,"Sequence number": 47018829, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1514 + } + }, + { + "ph": "f", "id": 163, "pid": 1336753, "tid": 1381210, "ts": 1712359476327.793, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476329.007, "dur": 3.648, + "args": { + "External id": 4726764,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476331.722, "dur": 0.849, + "args": { + "External id": 4726765,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476338.411, "dur": 89.551, + "args": { + "External id": 4726766,"Record function id": 0, "Sequence number": 47018828, "Fwd thread id": 1, "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476339.159, "dur": 83.456, + "args": { + "External id": 4726767,"Sequence number": 47018828, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1518 + } + }, + { + "ph": "f", "id": 164, "pid": 1336753, "tid": 1381210, "ts": 1712359476339.159, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476342.335, "dur": 2.831, + "args": { + "External id": 4726768,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476343.240, "dur": 1.562, + "args": { + "External id": 4726769,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476344.163, "dur": 0.548, + "args": { + "External id": 4726770,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359476345.971, "dur": 25.510, + "args": { + "External id": 4726771,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476374.480, "dur": 3.312, + "args": { + "External id": 4726772,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476375.187, "dur": 2.036, + "args": { + "External id": 4726773,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476375.944, "dur": 1.161, + "args": { + "External id": 4726774,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476379.018, "dur": 6.921, + "args": { + "External id": 4726775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476380.104, "dur": 5.426, + "args": { + "External id": 4726776,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476383.240, "dur": 2.182, + "args": { + "External id": 4726777,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359476388.316, "dur": 33.531, + "args": { + "External id": 4726778,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476434.032, "dur": 34.056, + "args": { + "External id": 4726779,"Record function id": 0, "Sequence number": 47018827, "Fwd thread id": 1, "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476435.049, "dur": 6.951, + "args": { + "External id": 4726780,"Sequence number": 47018827, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1531 + } + }, + { + "ph": "f", "id": 165, "pid": 1336753, "tid": 1381210, "ts": 1712359476435.049, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476436.441, "dur": 5.397, + "args": { + "External id": 4726781,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476440.894, "dur": 0.851, + "args": { + "External id": 4726782,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1381210, + "ts": 1712359476445.093, "dur": 20.944, + "args": { + "External id": 4726783,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476471.711, "dur": 91.558, + "args": { + "External id": 4726784,"Record function id": 0, "Sequence number": 47018826, "Fwd thread id": 1, "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476551.985, "dur": 8.666, + "args": { + "External id": 4726785,"Sequence number": 47018826, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1536 + } + }, + { + "ph": "f", "id": 166, "pid": 1336753, "tid": 1381210, "ts": 1712359476551.985, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476555.163, "dur": 5.289, + "args": { + "External id": 4726786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476556.031, "dur": 3.701, + "args": { + "External id": 4726787,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476559.034, "dur": 0.549, + "args": { + "External id": 4726788,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359476567.616, "dur": 4.859, + "args": { + "External id": 4726789,"Record function id": 0, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359476568.755, "dur": 3.166, + "args": { + "External id": 4726790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359476569.771, "dur": 1.742, + "args": { + "External id": 4726791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359476570.420, "dur": 1.003, + "args": { + "External id": 4726792,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476575.701, "dur": 7.526, + "args": { + "External id": 4726793,"Record function id": 0, "Sequence number": 47018825, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476576.475, "dur": 4.670, + "args": { + "External id": 4726794,"Sequence number": 47018825, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1545 + } + }, + { + "ph": "f", "id": 167, "pid": 1336753, "tid": 1381210, "ts": 1712359476576.475, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476577.378, "dur": 3.636, + "args": { + "External id": 4726795,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476579.771, "dur": 1.150, + "args": { + "External id": 4726796,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476586.294, "dur": 94.931, + "args": { + "External id": 4726797,"Record function id": 0, "Sequence number": 47018824, "Fwd thread id": 1, "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476587.223, "dur": 85.294, + "args": { + "External id": 4726798,"Sequence number": 47018824, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1549 + } + }, + { + "ph": "f", "id": 168, "pid": 1336753, "tid": 1381210, "ts": 1712359476587.223, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476590.080, "dur": 4.307, + "args": { + "External id": 4726799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476590.668, "dur": 3.295, + "args": { + "External id": 4726800,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476593.300, "dur": 0.547, + "args": { + "External id": 4726801,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359476595.078, "dur": 29.501, + "args": { + "External id": 4726802,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476627.250, "dur": 2.328, + "args": { + "External id": 4726803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476627.832, "dur": 1.261, + "args": { + "External id": 4726804,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476628.563, "dur": 0.414, + "args": { + "External id": 4726805,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476630.882, "dur": 2.471, + "args": { + "External id": 4726806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476631.839, "dur": 1.136, + "args": { + "External id": 4726807,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476632.383, "dur": 0.486, + "args": { + "External id": 4726808,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359476635.903, "dur": 35.921, + "args": { + "External id": 4726809,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476685.182, "dur": 25.746, + "args": { + "External id": 4726810,"Record function id": 0, "Sequence number": 47018823, "Fwd thread id": 1, "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476686.105, "dur": 4.688, + "args": { + "External id": 4726811,"Sequence number": 47018823, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1562 + } + }, + { + "ph": "f", "id": 169, "pid": 1336753, "tid": 1381210, "ts": 1712359476686.105, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476689.029, "dur": 1.600, + "args": { + "External id": 4726812,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476689.450, "dur": 1.045, + "args": { + "External id": 4726813,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359476693.287, "dur": 15.415, + "args": { + "External id": 4726814,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476714.613, "dur": 8.145, + "args": { + "External id": 4726815,"Record function id": 0, "Sequence number": 47018822, "Fwd thread id": 1, "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1712359476715.554, "dur": 5.247, + "args": { + "External id": 4726816,"Sequence number": 47018822, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1567 + } + }, + { + "ph": "f", "id": 170, "pid": 1336753, "tid": 1381210, "ts": 1712359476715.554, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1712359476716.355, "dur": 4.226, + "args": { + "External id": 4726817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1381210, + "ts": 1712359476716.955, "dur": 3.082, + "args": { + "External id": 4726818,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476719.408, "dur": 0.473, + "args": { + "External id": 4726819,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359476726.486, "dur": 4.290, + "args": { + "External id": 4726820,"Record function id": 0, "Ev Idx": 1571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359476727.602, "dur": 2.705, + "args": { + "External id": 4726821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359476728.548, "dur": 1.461, + "args": { + "External id": 4726822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359476728.921, "dur": 0.982, + "args": { + "External id": 4726823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359476734.750, "dur": 427.371, + "args": { + "External id": 4726824,"Record function id": 0, "Sequence number": 47018821, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359476737.813, "dur": 384.630, + "args": { + "External id": 4726825,"Sequence number": 47018821, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1576 + } + }, + { + "ph": "f", "id": 171, "pid": 1336753, "tid": 1381210, "ts": 1712359476737.813, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359476770.529, "dur": 1.623, + "args": { + "External id": 4726826,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476770.997, "dur": 1.004, + "args": { + "External id": 4726827,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359476787.516, "dur": 5.733, + "args": { + "External id": 4726828,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359476802.210, "dur": 2.044, + "args": { + "External id": 4726829,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359476951.212, "dur": 1.737, + "args": { + "External id": 4726830,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 1581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1712359476956.571, "dur": 77.921, + "args": { + "External id": 4726831,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 1582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359476968.329, "dur": 0.603, + "args": { + "External id": 4726832,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 1583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359477042.524, "dur": 50.274, + "args": { + "External id": 4726833,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 1584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359477044.595, "dur": 47.926, + "args": { + "External id": 4726834,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 1585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477048.924, "dur": 5.350, + "args": { + "External id": 4726835,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359477057.853, "dur": 33.743, + "args": { + "External id": 4726836,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 1587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1381210, + "ts": 1712359477099.003, "dur": 5.198, + "args": { + "External id": 4726837,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 1588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359477102.456, "dur": 1.635, + "args": { + "External id": 4726838,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 1589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1712359477112.414, "dur": 2.147, + "args": { + "External id": 4726839,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359477113.154, "dur": 1.296, + "args": { + "External id": 4726840,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1381210, + "ts": 1712359477141.101, "dur": 16.168, + "args": { + "External id": 4726841,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359477175.578, "dur": 11.234, + "args": { + "External id": 4726842,"Record function id": 0, "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359477177.580, "dur": 8.452, + "args": { + "External id": 4726843,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359477179.741, "dur": 5.130, + "args": { + "External id": 4726844,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359477182.793, "dur": 1.948, + "args": { + "External id": 4726845,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359477191.037, "dur": 2730.786, + "args": { + "External id": 4726846,"Record function id": 0, "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1712359477224.237, "dur": 1046.474, + "args": { + "External id": 4726847,"Record function id": 0, "Ev Idx": 1598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.26", "pid": 1336753, "tid": 1381210, + "ts": 1712359477251.793, "dur": 1009.315, + "args": { + "External id": 4726848,"Record function id": 0, "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1712359477268.969, "dur": 975.092, + "args": { + "External id": 4726849,"Record function id": 0, "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359477365.473, "dur": 7.451, + "args": { + "External id": 4726850,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359477392.814, "dur": 36.101, + "args": { + "External id": 4726851,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477398.964, "dur": 3.266, + "args": { + "External id": 4726852,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477403.411, "dur": 0.597, + "args": { + "External id": 4726853,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477408.601, "dur": 0.263, + "args": { + "External id": 4726854,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477409.694, "dur": 0.334, + "args": { + "External id": 4726855,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477410.474, "dur": 0.450, + "args": { + "External id": 4726856,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477414.452, "dur": 0.544, + "args": { + "External id": 4726857,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477416.081, "dur": 0.721, + "args": { + "External id": 4726858,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477417.308, "dur": 1.830, + "args": { + "External id": 4726859,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477421.524, "dur": 2.311, + "args": { + "External id": 4726860,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359477459.944, "dur": 36.581, + "args": { + "External id": 4726861,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359477538.752, "dur": 117.973, + "args": { + "External id": 4726862,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 1613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359477552.272, "dur": 6.611, + "args": { + "External id": 4726863,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359477565.462, "dur": 9.182, + "args": { + "External id": 4726864,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359477569.289, "dur": 4.949, + "args": { + "External id": 4726865,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 1616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477572.019, "dur": 0.752, + "args": { + "External id": 4726866,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359477581.564, "dur": 31.543, + "args": { + "External id": 4726867,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477584.645, "dur": 0.382, + "args": { + "External id": 4726868,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477586.001, "dur": 2.391, + "args": { + "External id": 4726869,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477589.220, "dur": 0.540, + "args": { + "External id": 4726870,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477592.176, "dur": 0.529, + "args": { + "External id": 4726871,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477595.359, "dur": 0.493, + "args": { + "External id": 4726872,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477596.667, "dur": 2.143, + "args": { + "External id": 4726873,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477601.555, "dur": 0.427, + "args": { + "External id": 4726874,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477604.198, "dur": 0.465, + "args": { + "External id": 4726875,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359477606.853, "dur": 0.425, + "args": { + "External id": 4726876,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359477624.370, "dur": 24.193, + "args": { + "External id": 4726877,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359477720.941, "dur": 410.209, + "args": { + "External id": 4726878,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 1629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359477757.683, "dur": 366.936, + "args": { + "External id": 4726879,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1630, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359477769.458, "dur": 348.407, + "args": { + "External id": 4726880,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 1631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359478157.815, "dur": 3.554, + "args": { + "External id": 4726881,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1632, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359478278.657, "dur": 1621.246, + "args": { + "External id": 4726882,"Sequence number": 47018820, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1633 + } + }, + { + "ph": "f", "id": 172, "pid": 1336753, "tid": 1381210, "ts": 1712359478278.657, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359478423.070, "dur": 102.191, + "args": { + "External id": 4726883,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 1634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359478571.565, "dur": 41.430, + "args": { + "External id": 4726884,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 1635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359478631.940, "dur": 45.549, + "args": { + "External id": 4726885,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 1636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359478687.417, "dur": 34.005, + "args": { + "External id": 4726886,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359478728.050, "dur": 45.787, + "args": { + "External id": 4726887,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359478781.532, "dur": 27.912, + "args": { + "External id": 4726888,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359478816.917, "dur": 43.115, + "args": { + "External id": 4726889,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359478886.168, "dur": 23.341, + "args": { + "External id": 4726890,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 1641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359478928.854, "dur": 37.372, + "args": { + "External id": 4726891,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359479031.055, "dur": 23.809, + "args": { + "External id": 4726892,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359479089.567, "dur": 19.053, + "args": { + "External id": 4726893,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359479120.892, "dur": 34.989, + "args": { + "External id": 4726894,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359479159.951, "dur": 34.890, + "args": { + "External id": 4726895,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359479227.403, "dur": 170.756, + "args": { + "External id": 4726896,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359479307.414, "dur": 6.953, + "args": { + "External id": 4726897,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359479316.206, "dur": 2.057, + "args": { + "External id": 4726898,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359479436.733, "dur": 25.266, + "args": { + "External id": 4726899,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359479478.260, "dur": 14.214, + "args": { + "External id": 4726900,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359479500.353, "dur": 31.211, + "args": { + "External id": 4726901,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359479536.995, "dur": 34.269, + "args": { + "External id": 4726902,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359479577.977, "dur": 19.050, + "args": { + "External id": 4726903,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359479603.854, "dur": 29.262, + "args": { + "External id": 4726904,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359479638.525, "dur": 18.833, + "args": { + "External id": 4726905,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359479664.323, "dur": 29.531, + "args": { + "External id": 4726906,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359479714.846, "dur": 21.037, + "args": { + "External id": 4726907,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 1658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359479753.882, "dur": 24.481, + "args": { + "External id": 4726908,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359479798.262, "dur": 16.086, + "args": { + "External id": 4726909,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359479826.808, "dur": 12.365, + "args": { + "External id": 4726910,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359479858.052, "dur": 16.050, + "args": { + "External id": 4726911,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 1662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359479944.837, "dur": 14.778, + "args": { + "External id": 4726912,"Record function id": 0, "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359479948.374, "dur": 10.202, + "args": { + "External id": 4726913,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359479952.362, "dur": 5.127, + "args": { + "External id": 4726914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359479953.812, "dur": 3.578, + "args": { + "External id": 4726915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359479963.540, "dur": 7.396, + "args": { + "External id": 4726916,"Record function id": 0, "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359479967.031, "dur": 3.456, + "args": { + "External id": 4726917,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359479967.989, "dur": 1.924, + "args": { + "External id": 4726918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359479968.932, "dur": 0.883, + "args": { + "External id": 4726919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359479974.276, "dur": 4.763, + "args": { + "External id": 4726920,"Record function id": 0, "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359479975.689, "dur": 2.904, + "args": { + "External id": 4726921,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359479976.421, "dur": 1.771, + "args": { + "External id": 4726922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359479977.370, "dur": 0.714, + "args": { + "External id": 4726923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359479982.244, "dur": 46.338, + "args": { + "External id": 4726924,"Record function id": 0, "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359479983.412, "dur": 44.005, + "args": { + "External id": 4726925,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359479984.042, "dur": 42.326, + "args": { + "External id": 4726926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480022.108, "dur": 3.933, + "args": { + "External id": 4726927,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480034.078, "dur": 5.388, + "args": { + "External id": 4726928,"Record function id": 0, "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480035.550, "dur": 3.468, + "args": { + "External id": 4726929,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480036.843, "dur": 1.726, + "args": { + "External id": 4726930,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480037.564, "dur": 0.910, + "args": { + "External id": 4726931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480042.590, "dur": 4.457, + "args": { + "External id": 4726932,"Record function id": 0, "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480043.876, "dur": 2.660, + "args": { + "External id": 4726933,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480044.589, "dur": 1.395, + "args": { + "External id": 4726934,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480045.123, "dur": 0.748, + "args": { + "External id": 4726935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480050.427, "dur": 3.708, + "args": { + "External id": 4726936,"Record function id": 0, "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480051.640, "dur": 2.062, + "args": { + "External id": 4726937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480052.166, "dur": 1.139, + "args": { + "External id": 4726938,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480052.640, "dur": 0.597, + "args": { + "External id": 4726939,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480057.277, "dur": 5.441, + "args": { + "External id": 4726940,"Record function id": 0, "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480058.262, "dur": 4.049, + "args": { + "External id": 4726941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480058.905, "dur": 2.880, + "args": { + "External id": 4726942,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480061.006, "dur": 0.676, + "args": { + "External id": 4726943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480082.350, "dur": 5.958, + "args": { + "External id": 4726944,"Record function id": 0, "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359480084.091, "dur": 3.521, + "args": { + "External id": 4726945,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480085.021, "dur": 1.627, + "args": { + "External id": 4726946,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359480085.434, "dur": 1.063, + "args": { + "External id": 4726947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359480093.920, "dur": 162431.501, + "args": { + "External id": 4726948,"Record function id": 0, "Sequence number": 47018819, "Fwd thread id": 1, "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359480095.222, "dur": 162421.748, + "args": { + "External id": 4726949,"Sequence number": 47018819, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1700 + } + }, + { + "ph": "f", "id": 173, "pid": 1336753, "tid": 1381210, "ts": 1712359480095.222, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1712359480132.522, "dur": 54.051, + "args": { + "External id": 4726950,"Record function id": 0, "Ev Idx": 1701 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1712359480199.126, "dur": 94.344, + "args": { + "External id": 4726951,"Record function id": 0, "Ev Idx": 1702 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1712359480299.941, "dur": 162208.729, + "args": { + "External id": 4726952,"Record function id": 0, "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359480360.399, "dur": 8.005, + "args": { + "External id": 4726953,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359480380.558, "dur": 5.132, + "args": { + "External id": 4726954,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 1705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359480405.376, "dur": 161232.879, + "args": { + "External id": 4726955,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 1706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359480420.411, "dur": 161207.697, + "args": { + "External id": 4726956,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 1707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359480501.007, "dur": 5.566, + "args": { + "External id": 4726957,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359480515.591, "dur": 161069.972, + "args": { + "External id": 4726958,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 1709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359480518.251, "dur": 161066.382, + "args": { + "External id": 4726959,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 1710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359480521.955, "dur": 5.743, + "args": { + "External id": 4726960,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359480529.223, "dur": 161051.462, + "args": { + "External id": 4726961,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 1712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359641739.518, "dur": 10.421, + "args": { + "External id": 4726962,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 1713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359641743.238, "dur": 6.218, + "args": { + "External id": 4726963,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359641788.733, "dur": 395.012, + "args": { + "External id": 4726964,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 1715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359641822.738, "dur": 355.856, + "args": { + "External id": 4726965,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1716, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359641834.416, "dur": 337.290, + "args": { + "External id": 4726966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 1717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359642208.927, "dur": 2.143, + "args": { + "External id": 4726967,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1718, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642275.338, "dur": 7.538, + "args": { + "External id": 4726968,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642340.349, "dur": 1.557, + "args": { + "External id": 4726969,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642359.045, "dur": 1.290, + "args": { + "External id": 4726970,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642376.511, "dur": 3.955, + "args": { + "External id": 4726971,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642392.269, "dur": 0.960, + "args": { + "External id": 4726972,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642402.324, "dur": 0.748, + "args": { + "External id": 4726973,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642415.135, "dur": 0.884, + "args": { + "External id": 4726974,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642429.061, "dur": 2.340, + "args": { + "External id": 4726975,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642443.360, "dur": 0.961, + "args": { + "External id": 4726976,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359642539.816, "dur": 2785.285, + "args": { + "External id": 4726977,"Record function id": 0, "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1712359642560.719, "dur": 1082.134, + "args": { + "External id": 4726978,"Record function id": 0, "Ev Idx": 1729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1712359642576.073, "dur": 332.807, + "args": { + "External id": 4726979,"Record function id": 0, "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642661.122, "dur": 4.200, + "args": { + "External id": 4726980,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 1731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642668.599, "dur": 0.821, + "args": { + "External id": 4726981,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 1732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642671.003, "dur": 1.087, + "args": { + "External id": 4726982,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642673.639, "dur": 3.108, + "args": { + "External id": 4726983,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642679.872, "dur": 0.943, + "args": { + "External id": 4726984,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642682.115, "dur": 0.936, + "args": { + "External id": 4726985,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642684.402, "dur": 2.735, + "args": { + "External id": 4726986,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 1737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642688.554, "dur": 0.836, + "args": { + "External id": 4726987,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642694.257, "dur": 1.125, + "args": { + "External id": 4726988,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359642696.840, "dur": 1.295, + "args": { + "External id": 4726989,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359642717.781, "dur": 163.674, + "args": { + "External id": 4726990,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 1741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359642738.373, "dur": 138.862, + "args": { + "External id": 4726991,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 1742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359642761.731, "dur": 12.393, + "args": { + "External id": 4726992,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359642778.390, "dur": 69.889, + "args": { + "External id": 4726993,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 1744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359642780.865, "dur": 67.064, + "args": { + "External id": 4726994,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 1745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359642784.063, "dur": 8.776, + "args": { + "External id": 4726995,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359642796.693, "dur": 50.753, + "args": { + "External id": 4726996,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 1747 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.25", "pid": 1336753, "tid": 1381210, + "ts": 1712359643041.794, "dur": 592.890, + "args": { + "External id": 4726997,"Record function id": 0, "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1712359643059.259, "dur": 561.656, + "args": { + "External id": 4726998,"Record function id": 0, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359643138.488, "dur": 5.943, + "args": { + "External id": 4726999,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359643160.401, "dur": 37.566, + "args": { + "External id": 4727000,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643167.165, "dur": 3.239, + "args": { + "External id": 4727001,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643171.696, "dur": 0.419, + "args": { + "External id": 4727002,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643172.907, "dur": 0.456, + "args": { + "External id": 4727003,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643177.817, "dur": 0.397, + "args": { + "External id": 4727004,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643178.817, "dur": 0.341, + "args": { + "External id": 4727005,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643179.926, "dur": 0.277, + "args": { + "External id": 4727006,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643184.277, "dur": 2.391, + "args": { + "External id": 4727007,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643187.182, "dur": 0.515, + "args": { + "External id": 4727008,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643189.845, "dur": 1.432, + "args": { + "External id": 4727009,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359643218.146, "dur": 37.125, + "args": { + "External id": 4727010,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359643288.886, "dur": 104.855, + "args": { + "External id": 4727011,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 1762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359643298.451, "dur": 4.711, + "args": { + "External id": 4727012,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359643308.284, "dur": 11.371, + "args": { + "External id": 4727013,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359643312.432, "dur": 6.813, + "args": { + "External id": 4727014,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 1765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643317.281, "dur": 0.707, + "args": { + "External id": 4727015,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359643326.150, "dur": 26.821, + "args": { + "External id": 4727016,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643327.355, "dur": 0.487, + "args": { + "External id": 4727017,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643330.959, "dur": 1.723, + "args": { + "External id": 4727018,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643333.446, "dur": 0.442, + "args": { + "External id": 4727019,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643334.339, "dur": 2.284, + "args": { + "External id": 4727020,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643340.323, "dur": 0.252, + "args": { + "External id": 4727021,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643341.259, "dur": 0.409, + "args": { + "External id": 4727022,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643343.651, "dur": 0.279, + "args": { + "External id": 4727023,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643345.908, "dur": 0.491, + "args": { + "External id": 4727024,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359643346.865, "dur": 0.555, + "args": { + "External id": 4727025,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359643365.872, "dur": 20.574, + "args": { + "External id": 4727026,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359643436.532, "dur": 118.701, + "args": { + "External id": 4727027,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 1778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359643466.213, "dur": 85.985, + "args": { + "External id": 4727028,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1779, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359643477.046, "dur": 71.047, + "args": { + "External id": 4727029,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 1780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359643572.209, "dur": 1.657, + "args": { + "External id": 4727030,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1781, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359643649.978, "dur": 1653.207, + "args": { + "External id": 4727031,"Sequence number": 47018818, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1782 + } + }, + { + "ph": "f", "id": 174, "pid": 1336753, "tid": 1381210, "ts": 1712359643649.978, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359643758.565, "dur": 97.785, + "args": { + "External id": 4727032,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 1783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359643900.163, "dur": 41.912, + "args": { + "External id": 4727033,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 1784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359643958.837, "dur": 94.703, + "args": { + "External id": 4727034,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 1785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644080.846, "dur": 38.488, + "args": { + "External id": 4727035,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644129.436, "dur": 45.996, + "args": { + "External id": 4727036,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644182.981, "dur": 27.237, + "args": { + "External id": 4727037,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644217.716, "dur": 43.405, + "args": { + "External id": 4727038,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359644288.216, "dur": 24.503, + "args": { + "External id": 4727039,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 1790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359644336.600, "dur": 29.265, + "args": { + "External id": 4727040,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359644387.903, "dur": 18.094, + "args": { + "External id": 4727041,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359644423.069, "dur": 14.036, + "args": { + "External id": 4727042,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644445.029, "dur": 27.018, + "args": { + "External id": 4727043,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644475.453, "dur": 32.005, + "args": { + "External id": 4727044,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359644537.949, "dur": 165.792, + "args": { + "External id": 4727045,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359644616.070, "dur": 5.425, + "args": { + "External id": 4727046,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359644623.042, "dur": 2.221, + "args": { + "External id": 4727047,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359644744.479, "dur": 23.808, + "args": { + "External id": 4727048,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359644781.869, "dur": 14.224, + "args": { + "External id": 4727049,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644803.874, "dur": 31.081, + "args": { + "External id": 4727050,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644840.415, "dur": 34.192, + "args": { + "External id": 4727051,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644885.932, "dur": 20.093, + "args": { + "External id": 4727052,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644910.341, "dur": 29.602, + "args": { + "External id": 4727053,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644945.060, "dur": 19.430, + "args": { + "External id": 4727054,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359644970.611, "dur": 82.820, + "args": { + "External id": 4727055,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359645103.183, "dur": 24.929, + "args": { + "External id": 4727056,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 1807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359645148.314, "dur": 29.480, + "args": { + "External id": 4727057,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359645194.503, "dur": 16.296, + "args": { + "External id": 4727058,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359645233.880, "dur": 12.668, + "args": { + "External id": 4727059,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359645260.065, "dur": 15.188, + "args": { + "External id": 4727060,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 1811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645348.177, "dur": 14.684, + "args": { + "External id": 4727061,"Record function id": 0, "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645351.244, "dur": 10.771, + "args": { + "External id": 4727062,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645355.457, "dur": 5.669, + "args": { + "External id": 4727063,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645357.079, "dur": 3.942, + "args": { + "External id": 4727064,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645366.960, "dur": 4.843, + "args": { + "External id": 4727065,"Record function id": 0, "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645368.084, "dur": 3.278, + "args": { + "External id": 4727066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645369.280, "dur": 1.441, + "args": { + "External id": 4727067,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645369.882, "dur": 0.773, + "args": { + "External id": 4727068,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645375.275, "dur": 5.766, + "args": { + "External id": 4727069,"Record function id": 0, "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645376.249, "dur": 4.384, + "args": { + "External id": 4727070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645377.162, "dur": 2.979, + "args": { + "External id": 4727071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645377.778, "dur": 2.253, + "args": { + "External id": 4727072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645384.348, "dur": 4.411, + "args": { + "External id": 4727073,"Record function id": 0, "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645385.608, "dur": 2.751, + "args": { + "External id": 4727074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645386.408, "dur": 1.529, + "args": { + "External id": 4727075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645386.775, "dur": 1.098, + "args": { + "External id": 4727076,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645392.073, "dur": 4.845, + "args": { + "External id": 4727077,"Record function id": 0, "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645393.208, "dur": 3.334, + "args": { + "External id": 4727078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645394.390, "dur": 1.634, + "args": { + "External id": 4727079,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645395.142, "dur": 0.816, + "args": { + "External id": 4727080,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645400.140, "dur": 5.832, + "args": { + "External id": 4727081,"Record function id": 0, "Ev Idx": 1832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645403.128, "dur": 2.422, + "args": { + "External id": 4727082,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645403.954, "dur": 1.206, + "args": { + "External id": 4727083,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645404.541, "dur": 0.554, + "args": { + "External id": 4727084,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645409.344, "dur": 3.554, + "args": { + "External id": 4727085,"Record function id": 0, "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645410.280, "dur": 2.214, + "args": { + "External id": 4727086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645411.120, "dur": 0.960, + "args": { + "External id": 4727087,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645411.470, "dur": 0.544, + "args": { + "External id": 4727088,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645416.013, "dur": 5.340, + "args": { + "External id": 4727089,"Record function id": 0, "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645416.981, "dur": 3.988, + "args": { + "External id": 4727090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645417.574, "dur": 2.880, + "args": { + "External id": 4727091,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645419.819, "dur": 0.566, + "args": { + "External id": 4727092,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645424.570, "dur": 3.749, + "args": { + "External id": 4727093,"Record function id": 0, "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359645425.574, "dur": 2.367, + "args": { + "External id": 4727094,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645426.519, "dur": 0.986, + "args": { + "External id": 4727095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359645426.813, "dur": 0.620, + "args": { + "External id": 4727096,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359645432.290, "dur": 42276.876, + "args": { + "External id": 4727097,"Record function id": 0, "Sequence number": 47018817, "Fwd thread id": 1, "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359645433.632, "dur": 42267.412, + "args": { + "External id": 4727098,"Sequence number": 47018817, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1849 + } + }, + { + "ph": "f", "id": 175, "pid": 1336753, "tid": 1381210, "ts": 1712359645433.632, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1712359645462.296, "dur": 39.341, + "args": { + "External id": 4727099,"Record function id": 0, "Ev Idx": 1850 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1712359645509.496, "dur": 64.209, + "args": { + "External id": 4727100,"Record function id": 0, "Ev Idx": 1851 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1712359645581.036, "dur": 42112.574, + "args": { + "External id": 4727101,"Record function id": 0, "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359645669.547, "dur": 6.397, + "args": { + "External id": 4727102,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359645688.407, "dur": 6.879, + "args": { + "External id": 4727103,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 1854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359645712.732, "dur": 41156.418, + "args": { + "External id": 4727104,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 1855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359645725.904, "dur": 41134.440, + "args": { + "External id": 4727105,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 1856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359645797.646, "dur": 13.618, + "args": { + "External id": 4727106,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359645818.244, "dur": 41007.518, + "args": { + "External id": 4727107,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 1858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359645820.747, "dur": 41004.108, + "args": { + "External id": 4727108,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 1859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359645825.939, "dur": 5.168, + "args": { + "External id": 4727109,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359645832.729, "dur": 40988.613, + "args": { + "External id": 4727110,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 1861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359686959.699, "dur": 8.314, + "args": { + "External id": 4727111,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 1862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359686962.501, "dur": 5.127, + "args": { + "External id": 4727112,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359687031.694, "dur": 377.237, + "args": { + "External id": 4727113,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 1864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359687075.595, "dur": 328.595, + "args": { + "External id": 4727114,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1865, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359687089.840, "dur": 308.245, + "args": { + "External id": 4727115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 1866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359687429.712, "dur": 2.085, + "args": { + "External id": 4727116,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1867, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687489.160, "dur": 6.646, + "args": { + "External id": 4727117,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687537.754, "dur": 1.187, + "args": { + "External id": 4727118,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687553.699, "dur": 3.240, + "args": { + "External id": 4727119,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687569.919, "dur": 1.021, + "args": { + "External id": 4727120,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687581.811, "dur": 0.799, + "args": { + "External id": 4727121,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687593.993, "dur": 0.681, + "args": { + "External id": 4727122,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687604.288, "dur": 2.652, + "args": { + "External id": 4727123,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687617.438, "dur": 2.266, + "args": { + "External id": 4727124,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687632.204, "dur": 0.877, + "args": { + "External id": 4727125,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359687723.334, "dur": 2795.593, + "args": { + "External id": 4727126,"Record function id": 0, "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1712359687746.340, "dur": 1083.291, + "args": { + "External id": 4727127,"Record function id": 0, "Ev Idx": 1878 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1712359687760.240, "dur": 372.801, + "args": { + "External id": 4727128,"Record function id": 0, "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687839.138, "dur": 4.027, + "args": { + "External id": 4727129,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 1880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687846.113, "dur": 1.247, + "args": { + "External id": 4727130,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 1881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687849.142, "dur": 3.253, + "args": { + "External id": 4727131,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687854.101, "dur": 1.203, + "args": { + "External id": 4727132,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687858.318, "dur": 1.262, + "args": { + "External id": 4727133,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687860.875, "dur": 0.900, + "args": { + "External id": 4727134,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687865.138, "dur": 2.669, + "args": { + "External id": 4727135,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 1886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687869.200, "dur": 1.100, + "args": { + "External id": 4727136,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687873.709, "dur": 0.718, + "args": { + "External id": 4727137,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359687875.700, "dur": 1.127, + "args": { + "External id": 4727138,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359687892.844, "dur": 206.523, + "args": { + "External id": 4727139,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 1890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359687910.129, "dur": 183.747, + "args": { + "External id": 4727140,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 1891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359687927.953, "dur": 14.569, + "args": { + "External id": 4727141,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359687945.867, "dur": 105.225, + "args": { + "External id": 4727142,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 1893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359687950.517, "dur": 100.184, + "args": { + "External id": 4727143,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 1894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359687953.973, "dur": 4.934, + "args": { + "External id": 4727144,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359687960.421, "dur": 89.229, + "args": { + "External id": 4727145,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 1896 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.24", "pid": 1336753, "tid": 1381210, + "ts": 1712359688227.867, "dur": 594.140, + "args": { + "External id": 4727146,"Record function id": 0, "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1712359688244.760, "dur": 561.175, + "args": { + "External id": 4727147,"Record function id": 0, "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359688305.144, "dur": 5.347, + "args": { + "External id": 4727148,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359688325.430, "dur": 36.118, + "args": { + "External id": 4727149,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688331.557, "dur": 1.827, + "args": { + "External id": 4727150,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688336.413, "dur": 0.578, + "args": { + "External id": 4727151,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688337.744, "dur": 0.646, + "args": { + "External id": 4727152,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688341.059, "dur": 1.622, + "args": { + "External id": 4727153,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688343.449, "dur": 0.447, + "args": { + "External id": 4727154,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688346.486, "dur": 1.865, + "args": { + "External id": 4727155,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688350.852, "dur": 0.354, + "args": { + "External id": 4727156,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688351.945, "dur": 0.319, + "args": { + "External id": 4727157,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688354.831, "dur": 0.310, + "args": { + "External id": 4727158,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359688370.546, "dur": 32.980, + "args": { + "External id": 4727159,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359688432.479, "dur": 149.870, + "args": { + "External id": 4727160,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 1911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359688441.845, "dur": 3.374, + "args": { + "External id": 4727161,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359688450.237, "dur": 12.771, + "args": { + "External id": 4727162,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359688454.234, "dur": 8.333, + "args": { + "External id": 4727163,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 1914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688459.170, "dur": 2.168, + "args": { + "External id": 4727164,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359688469.024, "dur": 71.349, + "args": { + "External id": 4727165,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688470.358, "dur": 0.332, + "args": { + "External id": 4727166,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688474.023, "dur": 0.564, + "args": { + "External id": 4727167,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688518.489, "dur": 2.179, + "args": { + "External id": 4727168,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688524.227, "dur": 0.441, + "args": { + "External id": 4727169,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688525.369, "dur": 0.421, + "args": { + "External id": 4727170,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688526.289, "dur": 1.882, + "args": { + "External id": 4727171,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688530.225, "dur": 0.560, + "args": { + "External id": 4727172,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688531.227, "dur": 0.264, + "args": { + "External id": 4727173,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359688534.148, "dur": 0.372, + "args": { + "External id": 4727174,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359688552.303, "dur": 22.497, + "args": { + "External id": 4727175,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359688625.292, "dur": 117.845, + "args": { + "External id": 4727176,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 1927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359688655.708, "dur": 84.231, + "args": { + "External id": 4727177,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1928, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359688664.400, "dur": 71.452, + "args": { + "External id": 4727178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 1929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359688758.410, "dur": 1.973, + "args": { + "External id": 4727179,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1930, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359688836.647, "dur": 1657.751, + "args": { + "External id": 4727180,"Sequence number": 47018816, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1931 + } + }, + { + "ph": "f", "id": 176, "pid": 1336753, "tid": 1381210, "ts": 1712359688836.647, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359688946.103, "dur": 157.168, + "args": { + "External id": 4727181,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 1932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359689148.737, "dur": 37.776, + "args": { + "External id": 4727182,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 1933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359689204.214, "dur": 57.878, + "args": { + "External id": 4727183,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 1934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359689274.438, "dur": 35.102, + "args": { + "External id": 4727184,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359689314.886, "dur": 45.676, + "args": { + "External id": 4727185,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359689366.709, "dur": 26.855, + "args": { + "External id": 4727186,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359689410.548, "dur": 43.867, + "args": { + "External id": 4727187,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359689484.242, "dur": 24.463, + "args": { + "External id": 4727188,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 1939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359689527.894, "dur": 26.663, + "args": { + "External id": 4727189,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359689575.923, "dur": 18.844, + "args": { + "External id": 4727190,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359689612.467, "dur": 12.937, + "args": { + "External id": 4727191,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359689634.164, "dur": 27.084, + "args": { + "External id": 4727192,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359689664.422, "dur": 31.316, + "args": { + "External id": 4727193,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359689722.007, "dur": 167.380, + "args": { + "External id": 4727194,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359689798.144, "dur": 7.816, + "args": { + "External id": 4727195,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359689807.640, "dur": 2.151, + "args": { + "External id": 4727196,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359689921.858, "dur": 22.205, + "args": { + "External id": 4727197,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359689956.683, "dur": 14.410, + "args": { + "External id": 4727198,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359689978.070, "dur": 100.433, + "args": { + "External id": 4727199,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359690087.970, "dur": 38.637, + "args": { + "External id": 4727200,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359690136.390, "dur": 19.324, + "args": { + "External id": 4727201,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359690159.581, "dur": 41.208, + "args": { + "External id": 4727202,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359690213.514, "dur": 25.194, + "args": { + "External id": 4727203,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359690245.529, "dur": 32.605, + "args": { + "External id": 4727204,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359690307.099, "dur": 23.864, + "args": { + "External id": 4727205,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 1956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359690350.073, "dur": 26.587, + "args": { + "External id": 4727206,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359690390.942, "dur": 17.918, + "args": { + "External id": 4727207,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359690423.963, "dur": 12.696, + "args": { + "External id": 4727208,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359690450.819, "dur": 14.892, + "args": { + "External id": 4727209,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 1960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690544.652, "dur": 13.802, + "args": { + "External id": 4727210,"Record function id": 0, "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690547.678, "dur": 10.004, + "args": { + "External id": 4727211,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690551.409, "dur": 5.453, + "args": { + "External id": 4727212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690552.868, "dur": 3.891, + "args": { + "External id": 4727213,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690562.500, "dur": 8.023, + "args": { + "External id": 4727214,"Record function id": 0, "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690565.200, "dur": 4.807, + "args": { + "External id": 4727215,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690566.266, "dur": 3.222, + "args": { + "External id": 4727216,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690567.006, "dur": 2.399, + "args": { + "External id": 4727217,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690573.876, "dur": 4.626, + "args": { + "External id": 4727218,"Record function id": 0, "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690575.454, "dur": 2.618, + "args": { + "External id": 4727219,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690575.978, "dur": 1.685, + "args": { + "External id": 4727220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690576.704, "dur": 0.878, + "args": { + "External id": 4727221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690581.676, "dur": 3.782, + "args": { + "External id": 4727222,"Record function id": 0, "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690582.766, "dur": 2.290, + "args": { + "External id": 4727223,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690583.507, "dur": 1.133, + "args": { + "External id": 4727224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690583.982, "dur": 0.564, + "args": { + "External id": 4727225,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690588.729, "dur": 3.524, + "args": { + "External id": 4727226,"Record function id": 0, "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690589.666, "dur": 2.186, + "args": { + "External id": 4727227,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690590.209, "dur": 1.224, + "args": { + "External id": 4727228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690590.699, "dur": 0.640, + "args": { + "External id": 4727229,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690595.421, "dur": 3.661, + "args": { + "External id": 4727230,"Record function id": 0, "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690596.602, "dur": 2.027, + "args": { + "External id": 4727231,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690597.252, "dur": 0.943, + "args": { + "External id": 4727232,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690597.562, "dur": 0.540, + "args": { + "External id": 4727233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690602.532, "dur": 5.401, + "args": { + "External id": 4727234,"Record function id": 0, "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690603.579, "dur": 3.921, + "args": { + "External id": 4727235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690604.176, "dur": 2.909, + "args": { + "External id": 4727236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690606.440, "dur": 0.533, + "args": { + "External id": 4727237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690611.215, "dur": 3.809, + "args": { + "External id": 4727238,"Record function id": 0, "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690612.084, "dur": 2.534, + "args": { + "External id": 4727239,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690612.751, "dur": 1.452, + "args": { + "External id": 4727240,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690613.238, "dur": 0.873, + "args": { + "External id": 4727241,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690618.119, "dur": 6.112, + "args": { + "External id": 4727242,"Record function id": 0, "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359690619.338, "dur": 4.459, + "args": { + "External id": 4727243,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690619.994, "dur": 3.337, + "args": { + "External id": 4727244,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359690620.460, "dur": 2.804, + "args": { + "External id": 4727245,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359690628.440, "dur": 40237.535, + "args": { + "External id": 4727246,"Record function id": 0, "Sequence number": 47018815, "Fwd thread id": 1, "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359690629.930, "dur": 40227.827, + "args": { + "External id": 4727247,"Sequence number": 47018815, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1998 + } + }, + { + "ph": "f", "id": 177, "pid": 1336753, "tid": 1381210, "ts": 1712359690629.930, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1712359690663.420, "dur": 41.027, + "args": { + "External id": 4727248,"Record function id": 0, "Ev Idx": 1999 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1712359690711.344, "dur": 62.929, + "args": { + "External id": 4727249,"Record function id": 0, "Ev Idx": 2000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1712359690783.937, "dur": 40066.345, + "args": { + "External id": 4727250,"Record function id": 0, "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359690870.499, "dur": 6.381, + "args": { + "External id": 4727251,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359690887.167, "dur": 4.703, + "args": { + "External id": 4727252,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359690905.031, "dur": 39124.528, + "args": { + "External id": 4727253,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359690921.213, "dur": 39098.688, + "args": { + "External id": 4727254,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359690975.163, "dur": 51.419, + "args": { + "External id": 4727255,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359691034.162, "dur": 38922.645, + "args": { + "External id": 4727256,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359691036.939, "dur": 38919.028, + "args": { + "External id": 4727257,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359691040.561, "dur": 7.765, + "args": { + "External id": 4727258,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359691050.103, "dur": 38902.523, + "args": { + "External id": 4727259,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359730128.673, "dur": 8.238, + "args": { + "External id": 4727260,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359730131.631, "dur": 4.837, + "args": { + "External id": 4727261,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359730169.541, "dur": 400.820, + "args": { + "External id": 4727262,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359730201.674, "dur": 364.036, + "args": { + "External id": 4727263,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2014, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359730216.891, "dur": 343.239, + "args": { + "External id": 4727264,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359730593.236, "dur": 2.086, + "args": { + "External id": 4727265,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2016, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359730650.022, "dur": 6.460, + "args": { + "External id": 4727266,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359730700.989, "dur": 3.141, + "args": { + "External id": 4727267,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359730718.830, "dur": 1.133, + "args": { + "External id": 4727268,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359730732.099, "dur": 0.923, + "args": { + "External id": 4727269,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359730743.154, "dur": 1.032, + "args": { + "External id": 4727270,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359730753.295, "dur": 2.581, + "args": { + "External id": 4727271,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359730768.579, "dur": 0.963, + "args": { + "External id": 4727272,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359730779.626, "dur": 2.244, + "args": { + "External id": 4727273,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359730789.956, "dur": 1.052, + "args": { + "External id": 4727274,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359730879.801, "dur": 2817.149, + "args": { + "External id": 4727275,"Record function id": 0, "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1712359730898.682, "dur": 1154.172, + "args": { + "External id": 4727276,"Record function id": 0, "Ev Idx": 2027 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1712359730912.592, "dur": 379.862, + "args": { + "External id": 4727277,"Record function id": 0, "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731033.020, "dur": 6.443, + "args": { + "External id": 4727278,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731042.857, "dur": 1.213, + "args": { + "External id": 4727279,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731047.559, "dur": 0.940, + "args": { + "External id": 4727280,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731049.805, "dur": 0.923, + "args": { + "External id": 4727281,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731052.031, "dur": 0.903, + "args": { + "External id": 4727282,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731054.127, "dur": 0.997, + "args": { + "External id": 4727283,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731058.292, "dur": 2.259, + "args": { + "External id": 4727284,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731061.740, "dur": 1.044, + "args": { + "External id": 4727285,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731080.425, "dur": 3.566, + "args": { + "External id": 4727286,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359731087.017, "dur": 0.829, + "args": { + "External id": 4727287,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359731107.909, "dur": 153.883, + "args": { + "External id": 4727288,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359731126.395, "dur": 131.063, + "args": { + "External id": 4727289,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359731147.897, "dur": 12.203, + "args": { + "External id": 4727290,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359731163.526, "dur": 67.688, + "args": { + "External id": 4727291,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359731166.055, "dur": 64.810, + "args": { + "External id": 4727292,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731169.514, "dur": 7.727, + "args": { + "External id": 4727293,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359731178.889, "dur": 51.306, + "args": { + "External id": 4727294,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2045 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.23", "pid": 1336753, "tid": 1381210, + "ts": 1712359731381.436, "dur": 663.774, + "args": { + "External id": 4727295,"Record function id": 0, "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1712359731396.490, "dur": 634.361, + "args": { + "External id": 4727296,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359731532.034, "dur": 5.536, + "args": { + "External id": 4727297,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359731553.649, "dur": 33.103, + "args": { + "External id": 4727298,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731559.611, "dur": 3.053, + "args": { + "External id": 4727299,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731564.130, "dur": 0.350, + "args": { + "External id": 4727300,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731565.017, "dur": 0.302, + "args": { + "External id": 4727301,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731569.084, "dur": 1.989, + "args": { + "External id": 4727302,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731571.600, "dur": 0.321, + "args": { + "External id": 4727303,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731572.562, "dur": 0.262, + "args": { + "External id": 4727304,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731576.193, "dur": 0.243, + "args": { + "External id": 4727305,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731577.173, "dur": 0.373, + "args": { + "External id": 4727306,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731579.151, "dur": 1.675, + "args": { + "External id": 4727307,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359731595.552, "dur": 34.804, + "args": { + "External id": 4727308,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359731660.283, "dur": 103.762, + "args": { + "External id": 4727309,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359731669.841, "dur": 3.331, + "args": { + "External id": 4727310,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359731678.406, "dur": 9.694, + "args": { + "External id": 4727311,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359731682.361, "dur": 5.349, + "args": { + "External id": 4727312,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731686.252, "dur": 0.389, + "args": { + "External id": 4727313,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359731694.394, "dur": 25.478, + "args": { + "External id": 4727314,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731695.440, "dur": 2.161, + "args": { + "External id": 4727315,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731700.050, "dur": 0.296, + "args": { + "External id": 4727316,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731700.838, "dur": 1.895, + "args": { + "External id": 4727317,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731703.234, "dur": 0.288, + "args": { + "External id": 4727318,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731705.117, "dur": 0.297, + "args": { + "External id": 4727319,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731707.743, "dur": 0.248, + "args": { + "External id": 4727320,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731709.266, "dur": 0.277, + "args": { + "External id": 4727321,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731710.046, "dur": 0.238, + "args": { + "External id": 4727322,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359731712.323, "dur": 1.986, + "args": { + "External id": 4727323,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359731733.503, "dur": 19.707, + "args": { + "External id": 4727324,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359731806.674, "dur": 119.813, + "args": { + "External id": 4727325,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359731838.175, "dur": 84.935, + "args": { + "External id": 4727326,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2077, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359731847.255, "dur": 71.306, + "args": { + "External id": 4727327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359731942.806, "dur": 1.586, + "args": { + "External id": 4727328,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2079, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359732062.214, "dur": 1613.346, + "args": { + "External id": 4727329,"Sequence number": 47018814, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2080 + } + }, + { + "ph": "f", "id": 178, "pid": 1336753, "tid": 1381210, "ts": 1712359732062.214, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359732188.260, "dur": 107.101, + "args": { + "External id": 4727330,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359732341.015, "dur": 36.972, + "args": { + "External id": 4727331,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359732400.067, "dur": 50.174, + "args": { + "External id": 4727332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359732459.869, "dur": 32.745, + "args": { + "External id": 4727333,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359732499.255, "dur": 45.577, + "args": { + "External id": 4727334,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359732551.368, "dur": 27.374, + "args": { + "External id": 4727335,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359732587.749, "dur": 41.719, + "args": { + "External id": 4727336,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359732654.101, "dur": 25.788, + "args": { + "External id": 4727337,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359732702.241, "dur": 27.731, + "args": { + "External id": 4727338,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359732750.029, "dur": 19.004, + "args": { + "External id": 4727339,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359732784.545, "dur": 13.611, + "args": { + "External id": 4727340,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359732808.674, "dur": 27.803, + "args": { + "External id": 4727341,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359732839.640, "dur": 33.224, + "args": { + "External id": 4727342,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359732902.286, "dur": 229.290, + "args": { + "External id": 4727343,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359732979.461, "dur": 45.413, + "args": { + "External id": 4727344,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359733028.308, "dur": 2.298, + "args": { + "External id": 4727345,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359733171.649, "dur": 24.134, + "args": { + "External id": 4727346,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359733207.522, "dur": 13.788, + "args": { + "External id": 4727347,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359733230.260, "dur": 41.409, + "args": { + "External id": 4727348,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359733278.562, "dur": 35.593, + "args": { + "External id": 4727349,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359733322.439, "dur": 19.562, + "args": { + "External id": 4727350,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359733346.280, "dur": 41.685, + "args": { + "External id": 4727351,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359733400.110, "dur": 22.747, + "args": { + "External id": 4727352,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359733431.616, "dur": 32.296, + "args": { + "External id": 4727353,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359733488.471, "dur": 21.700, + "args": { + "External id": 4727354,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359733530.402, "dur": 26.289, + "args": { + "External id": 4727355,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359733571.917, "dur": 17.191, + "args": { + "External id": 4727356,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359733606.579, "dur": 12.699, + "args": { + "External id": 4727357,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359733632.259, "dur": 16.672, + "args": { + "External id": 4727358,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733719.374, "dur": 16.149, + "args": { + "External id": 4727359,"Record function id": 0, "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733722.662, "dur": 11.885, + "args": { + "External id": 4727360,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733727.097, "dur": 6.603, + "args": { + "External id": 4727361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733728.513, "dur": 5.086, + "args": { + "External id": 4727362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733739.268, "dur": 5.148, + "args": { + "External id": 4727363,"Record function id": 0, "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733740.690, "dur": 3.267, + "args": { + "External id": 4727364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733742.054, "dur": 1.438, + "args": { + "External id": 4727365,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733742.625, "dur": 0.759, + "args": { + "External id": 4727366,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733747.925, "dur": 4.557, + "args": { + "External id": 4727367,"Record function id": 0, "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733749.237, "dur": 2.824, + "args": { + "External id": 4727368,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733750.218, "dur": 1.400, + "args": { + "External id": 4727369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733750.921, "dur": 0.590, + "args": { + "External id": 4727370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733755.822, "dur": 4.548, + "args": { + "External id": 4727371,"Record function id": 0, "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733757.317, "dur": 2.648, + "args": { + "External id": 4727372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733758.007, "dur": 1.432, + "args": { + "External id": 4727373,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733758.574, "dur": 0.773, + "args": { + "External id": 4727374,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733763.510, "dur": 3.542, + "args": { + "External id": 4727375,"Record function id": 0, "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733764.652, "dur": 2.011, + "args": { + "External id": 4727376,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733765.350, "dur": 0.912, + "args": { + "External id": 4727377,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733765.631, "dur": 0.535, + "args": { + "External id": 4727378,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733770.431, "dur": 3.399, + "args": { + "External id": 4727379,"Record function id": 0, "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733771.490, "dur": 1.922, + "args": { + "External id": 4727380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733771.954, "dur": 1.049, + "args": { + "External id": 4727381,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733772.306, "dur": 0.605, + "args": { + "External id": 4727382,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733777.135, "dur": 5.462, + "args": { + "External id": 4727383,"Record function id": 0, "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733778.304, "dur": 3.878, + "args": { + "External id": 4727384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733778.745, "dur": 2.912, + "args": { + "External id": 4727385,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733781.023, "dur": 0.539, + "args": { + "External id": 4727386,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733785.776, "dur": 5.205, + "args": { + "External id": 4727387,"Record function id": 0, "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733786.790, "dur": 3.791, + "args": { + "External id": 4727388,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733787.295, "dur": 2.851, + "args": { + "External id": 4727389,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733787.570, "dur": 2.511, + "args": { + "External id": 4727390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733794.089, "dur": 4.441, + "args": { + "External id": 4727391,"Record function id": 0, "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359733795.253, "dur": 2.876, + "args": { + "External id": 4727392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733795.952, "dur": 1.515, + "args": { + "External id": 4727393,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359733796.409, "dur": 0.965, + "args": { + "External id": 4727394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359733802.226, "dur": 38494.346, + "args": { + "External id": 4727395,"Record function id": 0, "Sequence number": 47018813, "Fwd thread id": 1, "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359733803.687, "dur": 38484.531, + "args": { + "External id": 4727396,"Sequence number": 47018813, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2147 + } + }, + { + "ph": "f", "id": 179, "pid": 1336753, "tid": 1381210, "ts": 1712359733803.687, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1712359733831.136, "dur": 37.666, + "args": { + "External id": 4727397,"Record function id": 0, "Ev Idx": 2148 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1712359733876.518, "dur": 64.112, + "args": { + "External id": 4727398,"Record function id": 0, "Ev Idx": 2149 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1712359733947.882, "dur": 38332.114, + "args": { + "External id": 4727399,"Record function id": 0, "Ev Idx": 2150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359734103.261, "dur": 7.875, + "args": { + "External id": 4727400,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359734122.181, "dur": 8.298, + "args": { + "External id": 4727401,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359734146.105, "dur": 37296.095, + "args": { + "External id": 4727402,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359734160.017, "dur": 37273.469, + "args": { + "External id": 4727403,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359734216.773, "dur": 13.221, + "args": { + "External id": 4727404,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359734236.120, "dur": 37160.508, + "args": { + "External id": 4727405,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359734239.855, "dur": 37156.049, + "args": { + "External id": 4727406,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359734247.205, "dur": 4.961, + "args": { + "External id": 4727407,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359734254.144, "dur": 37138.432, + "args": { + "External id": 4727408,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359771535.570, "dur": 8.752, + "args": { + "External id": 4727409,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359771538.717, "dur": 5.211, + "args": { + "External id": 4727410,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359771573.588, "dur": 347.560, + "args": { + "External id": 4727411,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359771603.274, "dur": 313.501, + "args": { + "External id": 4727412,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2163, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359771613.391, "dur": 298.255, + "args": { + "External id": 4727413,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359771942.509, "dur": 2.034, + "args": { + "External id": 4727414,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2165, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772045.677, "dur": 6.818, + "args": { + "External id": 4727415,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772114.736, "dur": 1.979, + "args": { + "External id": 4727416,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772134.253, "dur": 1.155, + "args": { + "External id": 4727417,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772147.567, "dur": 1.153, + "args": { + "External id": 4727418,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772162.457, "dur": 1.093, + "args": { + "External id": 4727419,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772176.519, "dur": 0.802, + "args": { + "External id": 4727420,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772189.605, "dur": 1.063, + "args": { + "External id": 4727421,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772202.211, "dur": 2.054, + "args": { + "External id": 4727422,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772217.230, "dur": 0.721, + "args": { + "External id": 4727423,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359772313.828, "dur": 2660.532, + "args": { + "External id": 4727424,"Record function id": 0, "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1712359772334.083, "dur": 1032.449, + "args": { + "External id": 4727425,"Record function id": 0, "Ev Idx": 2176 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1712359772347.967, "dur": 324.487, + "args": { + "External id": 4727426,"Record function id": 0, "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772437.334, "dur": 3.716, + "args": { + "External id": 4727427,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772444.405, "dur": 1.367, + "args": { + "External id": 4727428,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772447.717, "dur": 1.009, + "args": { + "External id": 4727429,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772450.982, "dur": 0.781, + "args": { + "External id": 4727430,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772455.167, "dur": 0.772, + "args": { + "External id": 4727431,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772457.306, "dur": 0.780, + "args": { + "External id": 4727432,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772460.282, "dur": 1.704, + "args": { + "External id": 4727433,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772464.039, "dur": 2.401, + "args": { + "External id": 4727434,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772469.957, "dur": 0.669, + "args": { + "External id": 4727435,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359772472.032, "dur": 0.799, + "args": { + "External id": 4727436,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359772490.532, "dur": 150.798, + "args": { + "External id": 4727437,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359772507.276, "dur": 129.687, + "args": { + "External id": 4727438,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359772526.492, "dur": 14.487, + "args": { + "External id": 4727439,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359772544.118, "dur": 66.273, + "args": { + "External id": 4727440,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359772546.652, "dur": 63.446, + "args": { + "External id": 4727441,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772550.146, "dur": 5.030, + "args": { + "External id": 4727442,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359772558.809, "dur": 50.602, + "args": { + "External id": 4727443,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2194 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.22", "pid": 1336753, "tid": 1381210, + "ts": 1712359772759.434, "dur": 599.171, + "args": { + "External id": 4727444,"Record function id": 0, "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1712359772775.207, "dur": 570.334, + "args": { + "External id": 4727445,"Record function id": 0, "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359772831.113, "dur": 4.649, + "args": { + "External id": 4727446,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359772851.383, "dur": 29.132, + "args": { + "External id": 4727447,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772855.758, "dur": 1.167, + "args": { + "External id": 4727448,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772859.495, "dur": 0.413, + "args": { + "External id": 4727449,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772861.185, "dur": 2.256, + "args": { + "External id": 4727450,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772864.856, "dur": 1.124, + "args": { + "External id": 4727451,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772867.521, "dur": 0.455, + "args": { + "External id": 4727452,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772869.450, "dur": 0.477, + "args": { + "External id": 4727453,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772872.041, "dur": 0.323, + "args": { + "External id": 4727454,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772874.241, "dur": 0.533, + "args": { + "External id": 4727455,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772876.298, "dur": 0.234, + "args": { + "External id": 4727456,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359772890.150, "dur": 29.478, + "args": { + "External id": 4727457,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359772949.089, "dur": 166.743, + "args": { + "External id": 4727458,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359772957.895, "dur": 2.930, + "args": { + "External id": 4727459,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359772965.713, "dur": 11.594, + "args": { + "External id": 4727460,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359772969.648, "dur": 7.224, + "args": { + "External id": 4727461,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359772972.999, "dur": 2.664, + "args": { + "External id": 4727462,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359773028.236, "dur": 25.993, + "args": { + "External id": 4727463,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359773031.132, "dur": 0.507, + "args": { + "External id": 4727464,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359773033.379, "dur": 0.390, + "args": { + "External id": 4727465,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359773035.131, "dur": 0.442, + "args": { + "External id": 4727466,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359773037.673, "dur": 0.252, + "args": { + "External id": 4727467,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359773039.540, "dur": 0.323, + "args": { + "External id": 4727468,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359773041.184, "dur": 1.498, + "args": { + "External id": 4727469,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359773043.913, "dur": 0.270, + "args": { + "External id": 4727470,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359773045.282, "dur": 2.104, + "args": { + "External id": 4727471,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359773049.325, "dur": 0.424, + "args": { + "External id": 4727472,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359773081.015, "dur": 25.955, + "args": { + "External id": 4727473,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359773163.153, "dur": 115.309, + "args": { + "External id": 4727474,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359773193.445, "dur": 81.723, + "args": { + "External id": 4727475,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2226, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359773202.849, "dur": 68.054, + "args": { + "External id": 4727476,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359773295.838, "dur": 1.619, + "args": { + "External id": 4727477,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2228, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359773374.371, "dur": 1579.866, + "args": { + "External id": 4727478,"Sequence number": 47018812, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2229 + } + }, + { + "ph": "f", "id": 180, "pid": 1336753, "tid": 1381210, "ts": 1712359773374.371, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359773484.837, "dur": 104.480, + "args": { + "External id": 4727479,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359773630.286, "dur": 39.525, + "args": { + "External id": 4727480,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359773687.310, "dur": 46.537, + "args": { + "External id": 4727481,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359773743.423, "dur": 30.995, + "args": { + "External id": 4727482,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359773780.561, "dur": 44.047, + "args": { + "External id": 4727483,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359773831.767, "dur": 26.569, + "args": { + "External id": 4727484,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359773867.165, "dur": 41.181, + "args": { + "External id": 4727485,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359773933.768, "dur": 21.830, + "args": { + "External id": 4727486,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359773974.079, "dur": 73.234, + "args": { + "External id": 4727487,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359774087.696, "dur": 22.160, + "args": { + "External id": 4727488,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359774126.581, "dur": 15.400, + "args": { + "External id": 4727489,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359774158.675, "dur": 34.133, + "args": { + "External id": 4727490,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359774196.822, "dur": 36.226, + "args": { + "External id": 4727491,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359774259.574, "dur": 169.673, + "args": { + "External id": 4727492,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359774336.301, "dur": 6.159, + "args": { + "External id": 4727493,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359774344.648, "dur": 2.010, + "args": { + "External id": 4727494,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359774461.159, "dur": 23.502, + "args": { + "External id": 4727495,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359774495.637, "dur": 14.789, + "args": { + "External id": 4727496,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359774520.369, "dur": 31.172, + "args": { + "External id": 4727497,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359774558.115, "dur": 33.905, + "args": { + "External id": 4727498,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359774608.665, "dur": 20.959, + "args": { + "External id": 4727499,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359774635.135, "dur": 30.419, + "args": { + "External id": 4727500,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359774674.563, "dur": 19.731, + "args": { + "External id": 4727501,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359774701.873, "dur": 45.955, + "args": { + "External id": 4727502,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359774769.684, "dur": 22.097, + "args": { + "External id": 4727503,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359774808.255, "dur": 24.069, + "args": { + "External id": 4727504,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359774846.123, "dur": 15.966, + "args": { + "External id": 4727505,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359774881.131, "dur": 14.033, + "args": { + "External id": 4727506,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359774906.493, "dur": 15.253, + "args": { + "External id": 4727507,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775037.389, "dur": 17.537, + "args": { + "External id": 4727508,"Record function id": 0, "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775041.532, "dur": 12.053, + "args": { + "External id": 4727509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775045.725, "dur": 6.447, + "args": { + "External id": 4727510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775047.750, "dur": 4.113, + "args": { + "External id": 4727511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775058.970, "dur": 20.066, + "args": { + "External id": 4727512,"Record function id": 0, "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775060.436, "dur": 16.902, + "args": { + "External id": 4727513,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775061.111, "dur": 2.233, + "args": { + "External id": 4727514,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775062.139, "dur": 1.117, + "args": { + "External id": 4727515,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775084.825, "dur": 6.117, + "args": { + "External id": 4727516,"Record function id": 0, "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775086.555, "dur": 3.983, + "args": { + "External id": 4727517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775087.642, "dur": 2.043, + "args": { + "External id": 4727518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775088.067, "dur": 1.531, + "args": { + "External id": 4727519,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775094.182, "dur": 3.626, + "args": { + "External id": 4727520,"Record function id": 0, "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775095.414, "dur": 2.002, + "args": { + "External id": 4727521,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775095.942, "dur": 1.013, + "args": { + "External id": 4727522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775096.274, "dur": 0.617, + "args": { + "External id": 4727523,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775100.929, "dur": 7.444, + "args": { + "External id": 4727524,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775105.652, "dur": 2.343, + "args": { + "External id": 4727525,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775106.115, "dur": 1.415, + "args": { + "External id": 4727526,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775106.731, "dur": 0.734, + "args": { + "External id": 4727527,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775111.593, "dur": 3.740, + "args": { + "External id": 4727528,"Record function id": 0, "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775112.716, "dur": 2.190, + "args": { + "External id": 4727529,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775113.160, "dur": 1.220, + "args": { + "External id": 4727530,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775113.652, "dur": 0.621, + "args": { + "External id": 4727531,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775118.752, "dur": 5.919, + "args": { + "External id": 4727532,"Record function id": 0, "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775119.851, "dur": 4.416, + "args": { + "External id": 4727533,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775120.365, "dur": 3.443, + "args": { + "External id": 4727534,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775120.780, "dur": 2.950, + "args": { + "External id": 4727535,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775127.818, "dur": 3.896, + "args": { + "External id": 4727536,"Record function id": 0, "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775128.983, "dur": 2.323, + "args": { + "External id": 4727537,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775129.489, "dur": 1.336, + "args": { + "External id": 4727538,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775129.932, "dur": 0.794, + "args": { + "External id": 4727539,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775134.803, "dur": 3.883, + "args": { + "External id": 4727540,"Record function id": 0, "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359775136.111, "dur": 2.138, + "args": { + "External id": 4727541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775136.578, "dur": 1.248, + "args": { + "External id": 4727542,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359775137.149, "dur": 0.571, + "args": { + "External id": 4727543,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359775142.781, "dur": 37826.731, + "args": { + "External id": 4727544,"Record function id": 0, "Sequence number": 47018811, "Fwd thread id": 1, "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359775144.291, "dur": 37816.737, + "args": { + "External id": 4727545,"Sequence number": 47018811, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2296 + } + }, + { + "ph": "f", "id": 181, "pid": 1336753, "tid": 1381210, "ts": 1712359775144.291, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1712359775179.148, "dur": 37.138, + "args": { + "External id": 4727546,"Record function id": 0, "Ev Idx": 2297 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1712359775228.185, "dur": 69.388, + "args": { + "External id": 4727547,"Record function id": 0, "Ev Idx": 2298 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1712359775303.238, "dur": 37649.855, + "args": { + "External id": 4727548,"Record function id": 0, "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359775397.507, "dur": 9.958, + "args": { + "External id": 4727549,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359775416.706, "dur": 4.660, + "args": { + "External id": 4727550,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359775435.749, "dur": 36703.256, + "args": { + "External id": 4727551,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359775449.404, "dur": 36678.253, + "args": { + "External id": 4727552,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359775503.211, "dur": 16.327, + "args": { + "External id": 4727553,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359775526.088, "dur": 36558.841, + "args": { + "External id": 4727554,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359775529.063, "dur": 36554.738, + "args": { + "External id": 4727555,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359775533.236, "dur": 5.068, + "args": { + "External id": 4727556,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359775540.498, "dur": 36539.302, + "args": { + "External id": 4727557,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359812237.971, "dur": 10.633, + "args": { + "External id": 4727558,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359812241.758, "dur": 6.467, + "args": { + "External id": 4727559,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359812280.078, "dur": 367.800, + "args": { + "External id": 4727560,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359812307.088, "dur": 335.605, + "args": { + "External id": 4727561,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2312, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359812318.374, "dur": 317.605, + "args": { + "External id": 4727562,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359812667.737, "dur": 2.246, + "args": { + "External id": 4727563,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2314, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359812730.471, "dur": 8.836, + "args": { + "External id": 4727564,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359812783.712, "dur": 1.249, + "args": { + "External id": 4727565,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359812805.305, "dur": 0.942, + "args": { + "External id": 4727566,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359812819.427, "dur": 0.927, + "args": { + "External id": 4727567,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359812833.780, "dur": 2.573, + "args": { + "External id": 4727568,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359812847.991, "dur": 1.081, + "args": { + "External id": 4727569,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359812864.671, "dur": 0.910, + "args": { + "External id": 4727570,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359812878.452, "dur": 2.085, + "args": { + "External id": 4727571,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359812892.520, "dur": 2.468, + "args": { + "External id": 4727572,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359813028.658, "dur": 2722.639, + "args": { + "External id": 4727573,"Record function id": 0, "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1712359813052.584, "dur": 1067.054, + "args": { + "External id": 4727574,"Record function id": 0, "Ev Idx": 2325 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1712359813081.723, "dur": 326.956, + "args": { + "External id": 4727575,"Record function id": 0, "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813168.791, "dur": 4.887, + "args": { + "External id": 4727576,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813177.157, "dur": 1.176, + "args": { + "External id": 4727577,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813180.131, "dur": 1.005, + "args": { + "External id": 4727578,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813182.951, "dur": 0.920, + "args": { + "External id": 4727579,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813185.391, "dur": 0.928, + "args": { + "External id": 4727580,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813188.228, "dur": 0.775, + "args": { + "External id": 4727581,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813190.790, "dur": 3.782, + "args": { + "External id": 4727582,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813196.141, "dur": 1.216, + "args": { + "External id": 4727583,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813198.834, "dur": 0.970, + "args": { + "External id": 4727584,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359813201.411, "dur": 1.119, + "args": { + "External id": 4727585,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359813220.556, "dur": 155.539, + "args": { + "External id": 4727586,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359813237.199, "dur": 134.984, + "args": { + "External id": 4727587,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359813260.788, "dur": 11.754, + "args": { + "External id": 4727588,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359813275.711, "dur": 67.629, + "args": { + "External id": 4727589,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359813278.594, "dur": 64.396, + "args": { + "External id": 4727590,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813282.995, "dur": 6.008, + "args": { + "External id": 4727591,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359813290.896, "dur": 51.574, + "args": { + "External id": 4727592,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2343 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.21", "pid": 1336753, "tid": 1381210, + "ts": 1712359813500.443, "dur": 609.676, + "args": { + "External id": 4727593,"Record function id": 0, "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1712359813516.768, "dur": 578.504, + "args": { + "External id": 4727594,"Record function id": 0, "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359813577.168, "dur": 8.145, + "args": { + "External id": 4727595,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359813600.986, "dur": 30.796, + "args": { + "External id": 4727596,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813605.897, "dur": 1.416, + "args": { + "External id": 4727597,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813609.478, "dur": 2.483, + "args": { + "External id": 4727598,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813613.872, "dur": 0.481, + "args": { + "External id": 4727599,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813616.231, "dur": 0.539, + "args": { + "External id": 4727600,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813618.665, "dur": 0.353, + "args": { + "External id": 4727601,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813620.651, "dur": 0.420, + "args": { + "External id": 4727602,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813622.412, "dur": 0.344, + "args": { + "External id": 4727603,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813624.493, "dur": 0.568, + "args": { + "External id": 4727604,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813626.647, "dur": 0.427, + "args": { + "External id": 4727605,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359813649.281, "dur": 33.054, + "args": { + "External id": 4727606,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359813712.853, "dur": 102.909, + "args": { + "External id": 4727607,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359813722.467, "dur": 4.737, + "args": { + "External id": 4727608,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359813732.772, "dur": 9.998, + "args": { + "External id": 4727609,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359813736.763, "dur": 5.582, + "args": { + "External id": 4727610,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813740.525, "dur": 0.622, + "args": { + "External id": 4727611,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359813749.528, "dur": 27.029, + "args": { + "External id": 4727612,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813752.010, "dur": 0.603, + "args": { + "External id": 4727613,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813754.676, "dur": 0.338, + "args": { + "External id": 4727614,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813756.719, "dur": 0.795, + "args": { + "External id": 4727615,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813759.146, "dur": 0.658, + "args": { + "External id": 4727616,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813761.353, "dur": 0.438, + "args": { + "External id": 4727617,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813763.592, "dur": 0.362, + "args": { + "External id": 4727618,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813765.823, "dur": 2.125, + "args": { + "External id": 4727619,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813769.541, "dur": 0.644, + "args": { + "External id": 4727620,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359813772.285, "dur": 0.407, + "args": { + "External id": 4727621,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359813788.829, "dur": 20.025, + "args": { + "External id": 4727622,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359813860.361, "dur": 107.460, + "args": { + "External id": 4727623,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359813882.494, "dur": 81.953, + "args": { + "External id": 4727624,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2375, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359813891.934, "dur": 68.214, + "args": { + "External id": 4727625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359814023.682, "dur": 3.011, + "args": { + "External id": 4727626,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2377, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359814127.935, "dur": 1603.077, + "args": { + "External id": 4727627,"Sequence number": 47018810, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2378 + } + }, + { + "ph": "f", "id": 182, "pid": 1336753, "tid": 1381210, "ts": 1712359814127.935, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359814238.432, "dur": 102.905, + "args": { + "External id": 4727628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359814383.101, "dur": 42.724, + "args": { + "External id": 4727629,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359814445.688, "dur": 46.800, + "args": { + "External id": 4727630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359814501.866, "dur": 31.397, + "args": { + "External id": 4727631,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359814539.901, "dur": 46.718, + "args": { + "External id": 4727632,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359814595.255, "dur": 28.170, + "args": { + "External id": 4727633,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359814630.554, "dur": 42.263, + "args": { + "External id": 4727634,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359814694.670, "dur": 21.286, + "args": { + "External id": 4727635,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359814743.916, "dur": 27.974, + "args": { + "External id": 4727636,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359814791.478, "dur": 18.254, + "args": { + "External id": 4727637,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359814823.742, "dur": 15.050, + "args": { + "External id": 4727638,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359814851.049, "dur": 28.226, + "args": { + "External id": 4727639,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359814882.431, "dur": 33.093, + "args": { + "External id": 4727640,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359814940.633, "dur": 243.886, + "args": { + "External id": 4727641,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359815056.729, "dur": 6.406, + "args": { + "External id": 4727642,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359815080.492, "dur": 5.585, + "args": { + "External id": 4727643,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359815218.727, "dur": 27.131, + "args": { + "External id": 4727644,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359815257.055, "dur": 14.676, + "args": { + "External id": 4727645,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359815280.706, "dur": 44.192, + "args": { + "External id": 4727646,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359815331.408, "dur": 36.335, + "args": { + "External id": 4727647,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359815374.786, "dur": 20.508, + "args": { + "External id": 4727648,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359815403.610, "dur": 29.918, + "args": { + "External id": 4727649,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359815440.999, "dur": 34.622, + "args": { + "External id": 4727650,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359815488.682, "dur": 34.859, + "args": { + "External id": 4727651,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359815541.938, "dur": 21.934, + "args": { + "External id": 4727652,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359815580.400, "dur": 23.412, + "args": { + "External id": 4727653,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359815617.476, "dur": 16.589, + "args": { + "External id": 4727654,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359815648.395, "dur": 14.047, + "args": { + "External id": 4727655,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359815683.813, "dur": 15.632, + "args": { + "External id": 4727656,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815773.755, "dur": 17.671, + "args": { + "External id": 4727657,"Record function id": 0, "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815777.012, "dur": 13.564, + "args": { + "External id": 4727658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815784.228, "dur": 5.538, + "args": { + "External id": 4727659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815785.801, "dur": 3.827, + "args": { + "External id": 4727660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815795.410, "dur": 5.816, + "args": { + "External id": 4727661,"Record function id": 0, "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815796.805, "dur": 3.963, + "args": { + "External id": 4727662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815797.985, "dur": 2.342, + "args": { + "External id": 4727663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815799.228, "dur": 1.011, + "args": { + "External id": 4727664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815804.785, "dur": 4.959, + "args": { + "External id": 4727665,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815806.368, "dur": 2.985, + "args": { + "External id": 4727666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815807.309, "dur": 1.595, + "args": { + "External id": 4727667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815807.816, "dur": 0.978, + "args": { + "External id": 4727668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815812.943, "dur": 6.041, + "args": { + "External id": 4727669,"Record function id": 0, "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815814.226, "dur": 4.361, + "args": { + "External id": 4727670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815814.987, "dur": 3.176, + "args": { + "External id": 4727671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815815.579, "dur": 2.513, + "args": { + "External id": 4727672,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815822.310, "dur": 4.019, + "args": { + "External id": 4727673,"Record function id": 0, "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815823.374, "dur": 2.549, + "args": { + "External id": 4727674,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815824.226, "dur": 1.180, + "args": { + "External id": 4727675,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815824.501, "dur": 0.824, + "args": { + "External id": 4727676,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815829.531, "dur": 4.594, + "args": { + "External id": 4727677,"Record function id": 0, "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815830.716, "dur": 3.016, + "args": { + "External id": 4727678,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815831.723, "dur": 1.617, + "args": { + "External id": 4727679,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815832.385, "dur": 0.847, + "args": { + "External id": 4727680,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815837.406, "dur": 4.652, + "args": { + "External id": 4727681,"Record function id": 0, "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815839.102, "dur": 2.557, + "args": { + "External id": 4727682,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815839.763, "dur": 1.503, + "args": { + "External id": 4727683,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815840.508, "dur": 0.680, + "args": { + "External id": 4727684,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815845.210, "dur": 4.047, + "args": { + "External id": 4727685,"Record function id": 0, "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815846.373, "dur": 2.498, + "args": { + "External id": 4727686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815847.356, "dur": 1.130, + "args": { + "External id": 4727687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815847.817, "dur": 0.588, + "args": { + "External id": 4727688,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815852.266, "dur": 3.743, + "args": { + "External id": 4727689,"Record function id": 0, "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359815853.282, "dur": 2.310, + "args": { + "External id": 4727690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815853.764, "dur": 1.390, + "args": { + "External id": 4727691,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359815854.254, "dur": 0.809, + "args": { + "External id": 4727692,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359815859.783, "dur": 36840.097, + "args": { + "External id": 4727693,"Record function id": 0, "Sequence number": 47018809, "Fwd thread id": 1, "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359815861.262, "dur": 36829.984, + "args": { + "External id": 4727694,"Sequence number": 47018809, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2445 + } + }, + { + "ph": "f", "id": 183, "pid": 1336753, "tid": 1381210, "ts": 1712359815861.262, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1712359815890.184, "dur": 36.125, + "args": { + "External id": 4727695,"Record function id": 0, "Ev Idx": 2446 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1712359815934.011, "dur": 114.509, + "args": { + "External id": 4727696,"Record function id": 0, "Ev Idx": 2447 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1712359816056.871, "dur": 36626.591, + "args": { + "External id": 4727697,"Record function id": 0, "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359816160.349, "dur": 7.135, + "args": { + "External id": 4727698,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359816177.809, "dur": 5.113, + "args": { + "External id": 4727699,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359816198.276, "dur": 35613.241, + "args": { + "External id": 4727700,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359816212.663, "dur": 35589.376, + "args": { + "External id": 4727701,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359816304.490, "dur": 15.660, + "args": { + "External id": 4727702,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359816326.598, "dur": 35435.797, + "args": { + "External id": 4727703,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359816329.298, "dur": 35432.093, + "args": { + "External id": 4727704,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359816333.672, "dur": 4.896, + "args": { + "External id": 4727705,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359816340.591, "dur": 35417.509, + "args": { + "External id": 4727706,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359851900.424, "dur": 9.334, + "args": { + "External id": 4727707,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359851904.040, "dur": 5.276, + "args": { + "External id": 4727708,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359851940.095, "dur": 435.531, + "args": { + "External id": 4727709,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359851966.314, "dur": 403.627, + "args": { + "External id": 4727710,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2461, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359851976.707, "dur": 387.194, + "args": { + "External id": 4727711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359852397.835, "dur": 2.303, + "args": { + "External id": 4727712,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2463, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359852463.875, "dur": 7.060, + "args": { + "External id": 4727713,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359852517.288, "dur": 2.440, + "args": { + "External id": 4727714,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359852536.673, "dur": 1.097, + "args": { + "External id": 4727715,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359852552.614, "dur": 0.879, + "args": { + "External id": 4727716,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359852565.724, "dur": 1.021, + "args": { + "External id": 4727717,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359852578.546, "dur": 1.225, + "args": { + "External id": 4727718,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359852591.102, "dur": 1.462, + "args": { + "External id": 4727719,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359852606.648, "dur": 2.124, + "args": { + "External id": 4727720,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359852620.783, "dur": 1.071, + "args": { + "External id": 4727721,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359852714.618, "dur": 2824.312, + "args": { + "External id": 4727722,"Record function id": 0, "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1712359852734.095, "dur": 1106.011, + "args": { + "External id": 4727723,"Record function id": 0, "Ev Idx": 2474 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1712359852749.958, "dur": 444.492, + "args": { + "External id": 4727724,"Record function id": 0, "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852830.191, "dur": 3.911, + "args": { + "External id": 4727725,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852837.096, "dur": 1.684, + "args": { + "External id": 4727726,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852840.576, "dur": 1.397, + "args": { + "External id": 4727727,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852843.437, "dur": 3.035, + "args": { + "External id": 4727728,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852848.012, "dur": 1.134, + "args": { + "External id": 4727729,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852850.782, "dur": 1.000, + "args": { + "External id": 4727730,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852853.426, "dur": 2.365, + "args": { + "External id": 4727731,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852857.237, "dur": 1.280, + "args": { + "External id": 4727732,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852860.385, "dur": 1.004, + "args": { + "External id": 4727733,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359852862.888, "dur": 1.115, + "args": { + "External id": 4727734,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359852883.896, "dur": 269.565, + "args": { + "External id": 4727735,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359852941.176, "dur": 205.981, + "args": { + "External id": 4727736,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359852959.556, "dur": 12.654, + "args": { + "External id": 4727737,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359852975.534, "dur": 141.610, + "args": { + "External id": 4727738,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359852978.471, "dur": 138.196, + "args": { + "External id": 4727739,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853034.399, "dur": 9.106, + "args": { + "External id": 4727740,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359853045.820, "dur": 69.738, + "args": { + "External id": 4727741,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2492 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.20", "pid": 1336753, "tid": 1381210, + "ts": 1712359853292.535, "dur": 539.043, + "args": { + "External id": 4727742,"Record function id": 0, "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1712359853310.608, "dur": 507.738, + "args": { + "External id": 4727743,"Record function id": 0, "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359853375.902, "dur": 5.607, + "args": { + "External id": 4727744,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359853397.287, "dur": 32.575, + "args": { + "External id": 4727745,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853402.451, "dur": 1.474, + "args": { + "External id": 4727746,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853406.252, "dur": 0.504, + "args": { + "External id": 4727747,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853408.736, "dur": 0.622, + "args": { + "External id": 4727748,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853411.429, "dur": 0.358, + "args": { + "External id": 4727749,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853413.331, "dur": 0.589, + "args": { + "External id": 4727750,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853415.751, "dur": 0.411, + "args": { + "External id": 4727751,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853417.842, "dur": 2.442, + "args": { + "External id": 4727752,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853421.931, "dur": 0.682, + "args": { + "External id": 4727753,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853424.093, "dur": 0.914, + "args": { + "External id": 4727754,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359853439.762, "dur": 30.478, + "args": { + "External id": 4727755,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359853503.600, "dur": 107.376, + "args": { + "External id": 4727756,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359853513.945, "dur": 2.972, + "args": { + "External id": 4727757,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359853522.263, "dur": 10.167, + "args": { + "External id": 4727758,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359853526.529, "dur": 5.509, + "args": { + "External id": 4727759,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853530.272, "dur": 0.627, + "args": { + "External id": 4727760,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359853542.888, "dur": 27.144, + "args": { + "External id": 4727761,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853545.352, "dur": 0.657, + "args": { + "External id": 4727762,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853548.023, "dur": 0.553, + "args": { + "External id": 4727763,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853550.569, "dur": 0.445, + "args": { + "External id": 4727764,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853552.915, "dur": 2.008, + "args": { + "External id": 4727765,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853556.730, "dur": 0.354, + "args": { + "External id": 4727766,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853558.742, "dur": 0.581, + "args": { + "External id": 4727767,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853560.955, "dur": 0.651, + "args": { + "External id": 4727768,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853563.340, "dur": 0.415, + "args": { + "External id": 4727769,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359853565.348, "dur": 0.428, + "args": { + "External id": 4727770,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359853580.755, "dur": 23.171, + "args": { + "External id": 4727771,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359853654.093, "dur": 106.519, + "args": { + "External id": 4727772,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359853675.104, "dur": 82.242, + "args": { + "External id": 4727773,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2524, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359853684.436, "dur": 68.690, + "args": { + "External id": 4727774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359853772.703, "dur": 1.908, + "args": { + "External id": 4727775,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2526, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359853847.755, "dur": 1668.215, + "args": { + "External id": 4727776,"Sequence number": 47018808, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2527 + } + }, + { + "ph": "f", "id": 184, "pid": 1336753, "tid": 1381210, "ts": 1712359853847.755, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359853954.569, "dur": 157.679, + "args": { + "External id": 4727777,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359854157.445, "dur": 41.423, + "args": { + "External id": 4727778,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359854217.358, "dur": 52.293, + "args": { + "External id": 4727779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359854279.142, "dur": 33.496, + "args": { + "External id": 4727780,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359854321.703, "dur": 47.290, + "args": { + "External id": 4727781,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359854376.527, "dur": 29.155, + "args": { + "External id": 4727782,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359854413.313, "dur": 42.744, + "args": { + "External id": 4727783,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359854479.346, "dur": 21.629, + "args": { + "External id": 4727784,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359854521.015, "dur": 28.458, + "args": { + "External id": 4727785,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359854568.586, "dur": 20.398, + "args": { + "External id": 4727786,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359854601.915, "dur": 13.882, + "args": { + "External id": 4727787,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359854625.308, "dur": 29.304, + "args": { + "External id": 4727788,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359854657.701, "dur": 32.598, + "args": { + "External id": 4727789,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359854718.918, "dur": 169.805, + "args": { + "External id": 4727790,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359854794.733, "dur": 5.348, + "args": { + "External id": 4727791,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359854802.578, "dur": 1.935, + "args": { + "External id": 4727792,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359854938.849, "dur": 23.202, + "args": { + "External id": 4727793,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359854974.881, "dur": 55.506, + "args": { + "External id": 4727794,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359855043.148, "dur": 56.591, + "args": { + "External id": 4727795,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359855108.832, "dur": 42.341, + "args": { + "External id": 4727796,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359855161.245, "dur": 26.817, + "args": { + "External id": 4727797,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359855202.315, "dur": 41.150, + "args": { + "External id": 4727798,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359855250.920, "dur": 20.222, + "args": { + "External id": 4727799,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359855279.713, "dur": 28.897, + "args": { + "External id": 4727800,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359855328.061, "dur": 23.758, + "args": { + "External id": 4727801,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359855371.596, "dur": 23.418, + "args": { + "External id": 4727802,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359855410.017, "dur": 19.941, + "args": { + "External id": 4727803,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359855445.342, "dur": 14.568, + "args": { + "External id": 4727804,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359855471.373, "dur": 16.033, + "args": { + "External id": 4727805,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855566.382, "dur": 134.900, + "args": { + "External id": 4727806,"Record function id": 0, "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855570.502, "dur": 128.222, + "args": { + "External id": 4727807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855576.048, "dur": 120.334, + "args": { + "External id": 4727808,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855690.417, "dur": 5.519, + "args": { + "External id": 4727809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855707.822, "dur": 6.246, + "args": { + "External id": 4727810,"Record function id": 0, "Ev Idx": 2561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855709.712, "dur": 3.810, + "args": { + "External id": 4727811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855710.910, "dur": 2.099, + "args": { + "External id": 4727812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855711.861, "dur": 1.035, + "args": { + "External id": 4727813,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855717.390, "dur": 6.373, + "args": { + "External id": 4727814,"Record function id": 0, "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855718.586, "dur": 4.743, + "args": { + "External id": 4727815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855719.112, "dur": 3.782, + "args": { + "External id": 4727816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855719.608, "dur": 3.225, + "args": { + "External id": 4727817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855726.925, "dur": 3.901, + "args": { + "External id": 4727818,"Record function id": 0, "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855728.120, "dur": 2.299, + "args": { + "External id": 4727819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855728.728, "dur": 1.298, + "args": { + "External id": 4727820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855729.145, "dur": 0.816, + "args": { + "External id": 4727821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855733.767, "dur": 4.303, + "args": { + "External id": 4727822,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855735.294, "dur": 2.371, + "args": { + "External id": 4727823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855735.908, "dur": 1.327, + "args": { + "External id": 4727824,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855736.321, "dur": 0.852, + "args": { + "External id": 4727825,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855741.105, "dur": 3.900, + "args": { + "External id": 4727826,"Record function id": 0, "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855742.444, "dur": 2.139, + "args": { + "External id": 4727827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855743.100, "dur": 1.027, + "args": { + "External id": 4727828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855743.488, "dur": 0.556, + "args": { + "External id": 4727829,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855748.298, "dur": 3.555, + "args": { + "External id": 4727830,"Record function id": 0, "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855749.413, "dur": 2.039, + "args": { + "External id": 4727831,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855749.986, "dur": 0.901, + "args": { + "External id": 4727832,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855750.265, "dur": 0.559, + "args": { + "External id": 4727833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855754.842, "dur": 5.517, + "args": { + "External id": 4727834,"Record function id": 0, "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855755.923, "dur": 4.040, + "args": { + "External id": 4727835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855756.710, "dur": 2.727, + "args": { + "External id": 4727836,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855758.729, "dur": 0.609, + "args": { + "External id": 4727837,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855763.267, "dur": 3.975, + "args": { + "External id": 4727838,"Record function id": 0, "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359855764.420, "dur": 2.423, + "args": { + "External id": 4727839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855765.177, "dur": 1.061, + "args": { + "External id": 4727840,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359855765.588, "dur": 0.586, + "args": { + "External id": 4727841,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359855771.250, "dur": 36846.125, + "args": { + "External id": 4727842,"Record function id": 0, "Sequence number": 47018807, "Fwd thread id": 1, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359855772.853, "dur": 36836.582, + "args": { + "External id": 4727843,"Sequence number": 47018807, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2594 + } + }, + { + "ph": "f", "id": 185, "pid": 1336753, "tid": 1381210, "ts": 1712359855772.853, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1712359855806.393, "dur": 39.935, + "args": { + "External id": 4727844,"Record function id": 0, "Ev Idx": 2595 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1712359855855.087, "dur": 71.153, + "args": { + "External id": 4727845,"Record function id": 0, "Ev Idx": 2596 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1712359855932.694, "dur": 36668.508, + "args": { + "External id": 4727846,"Record function id": 0, "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359856059.884, "dur": 22.406, + "args": { + "External id": 4727847,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359856094.756, "dur": 7.734, + "args": { + "External id": 4727848,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359856123.058, "dur": 35729.080, + "args": { + "External id": 4727849,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359856137.027, "dur": 35706.130, + "args": { + "External id": 4727850,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359856193.724, "dur": 17.077, + "args": { + "External id": 4727851,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359856217.346, "dur": 35584.638, + "args": { + "External id": 4727852,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359856220.017, "dur": 35581.065, + "args": { + "External id": 4727853,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359856224.344, "dur": 5.928, + "args": { + "External id": 4727854,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359856232.617, "dur": 35565.368, + "args": { + "External id": 4727855,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359891942.213, "dur": 9.081, + "args": { + "External id": 4727856,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359891945.767, "dur": 5.187, + "args": { + "External id": 4727857,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359892004.668, "dur": 301.827, + "args": { + "External id": 4727858,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359892033.503, "dur": 267.915, + "args": { + "External id": 4727859,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2610, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359892044.827, "dur": 250.400, + "args": { + "External id": 4727860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359892326.423, "dur": 2.112, + "args": { + "External id": 4727861,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2612, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892387.219, "dur": 6.241, + "args": { + "External id": 4727862,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892438.807, "dur": 1.303, + "args": { + "External id": 4727863,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892457.972, "dur": 2.658, + "args": { + "External id": 4727864,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892473.080, "dur": 1.047, + "args": { + "External id": 4727865,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892487.725, "dur": 0.955, + "args": { + "External id": 4727866,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892500.227, "dur": 1.092, + "args": { + "External id": 4727867,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892512.928, "dur": 2.820, + "args": { + "External id": 4727868,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892527.615, "dur": 2.547, + "args": { + "External id": 4727869,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892541.129, "dur": 0.916, + "args": { + "External id": 4727870,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359892630.385, "dur": 2723.530, + "args": { + "External id": 4727871,"Record function id": 0, "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1712359892650.023, "dur": 1036.005, + "args": { + "External id": 4727872,"Record function id": 0, "Ev Idx": 2623 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1712359892664.539, "dur": 356.142, + "args": { + "External id": 4727873,"Record function id": 0, "Ev Idx": 2624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892745.181, "dur": 3.951, + "args": { + "External id": 4727874,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892752.322, "dur": 1.462, + "args": { + "External id": 4727875,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892755.484, "dur": 3.726, + "args": { + "External id": 4727876,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892760.857, "dur": 1.259, + "args": { + "External id": 4727877,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892763.477, "dur": 1.347, + "args": { + "External id": 4727878,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892766.418, "dur": 0.892, + "args": { + "External id": 4727879,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892769.117, "dur": 1.933, + "args": { + "External id": 4727880,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892772.510, "dur": 1.052, + "args": { + "External id": 4727881,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892774.964, "dur": 0.824, + "args": { + "External id": 4727882,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359892777.136, "dur": 0.917, + "args": { + "External id": 4727883,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359892798.221, "dur": 151.447, + "args": { + "External id": 4727884,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359892813.941, "dur": 131.959, + "args": { + "External id": 4727885,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359892834.674, "dur": 14.183, + "args": { + "External id": 4727886,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359892852.179, "dur": 66.058, + "args": { + "External id": 4727887,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359892854.776, "dur": 63.133, + "args": { + "External id": 4727888,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359892858.963, "dur": 5.160, + "args": { + "External id": 4727889,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359892866.287, "dur": 50.921, + "args": { + "External id": 4727890,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2641 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.19", "pid": 1336753, "tid": 1381210, + "ts": 1712359893141.848, "dur": 535.670, + "args": { + "External id": 4727891,"Record function id": 0, "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1712359893159.761, "dur": 504.889, + "args": { + "External id": 4727892,"Record function id": 0, "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359893221.159, "dur": 5.590, + "args": { + "External id": 4727893,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359893243.207, "dur": 31.581, + "args": { + "External id": 4727894,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893248.712, "dur": 1.827, + "args": { + "External id": 4727895,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893252.789, "dur": 0.572, + "args": { + "External id": 4727896,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893255.070, "dur": 0.609, + "args": { + "External id": 4727897,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893257.660, "dur": 0.602, + "args": { + "External id": 4727898,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893260.079, "dur": 0.408, + "args": { + "External id": 4727899,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893262.262, "dur": 1.713, + "args": { + "External id": 4727900,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893265.365, "dur": 0.407, + "args": { + "External id": 4727901,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893267.609, "dur": 0.380, + "args": { + "External id": 4727902,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893269.799, "dur": 0.366, + "args": { + "External id": 4727903,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359893284.785, "dur": 34.808, + "args": { + "External id": 4727904,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359893350.541, "dur": 101.327, + "args": { + "External id": 4727905,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359893360.717, "dur": 2.820, + "args": { + "External id": 4727906,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359893368.880, "dur": 10.464, + "args": { + "External id": 4727907,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359893373.129, "dur": 5.819, + "args": { + "External id": 4727908,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893377.266, "dur": 0.494, + "args": { + "External id": 4727909,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359893386.422, "dur": 26.003, + "args": { + "External id": 4727910,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893388.817, "dur": 0.596, + "args": { + "External id": 4727911,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893391.044, "dur": 0.295, + "args": { + "External id": 4727912,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893393.399, "dur": 2.352, + "args": { + "External id": 4727913,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893397.338, "dur": 0.348, + "args": { + "External id": 4727914,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893399.555, "dur": 0.435, + "args": { + "External id": 4727915,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893401.591, "dur": 0.288, + "args": { + "External id": 4727916,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893403.820, "dur": 0.399, + "args": { + "External id": 4727917,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893405.749, "dur": 0.339, + "args": { + "External id": 4727918,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359893407.960, "dur": 0.385, + "args": { + "External id": 4727919,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359893424.759, "dur": 19.925, + "args": { + "External id": 4727920,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359893496.860, "dur": 106.445, + "args": { + "External id": 4727921,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359893519.301, "dur": 80.534, + "args": { + "External id": 4727922,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2673, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359893528.565, "dur": 66.715, + "args": { + "External id": 4727923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359893615.876, "dur": 1.907, + "args": { + "External id": 4727924,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2675, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359893694.199, "dur": 1634.798, + "args": { + "External id": 4727925,"Sequence number": 47018806, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2676 + } + }, + { + "ph": "f", "id": 186, "pid": 1336753, "tid": 1381210, "ts": 1712359893694.199, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359893800.410, "dur": 99.261, + "args": { + "External id": 4727926,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359893936.265, "dur": 41.395, + "args": { + "External id": 4727927,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894040.255, "dur": 72.503, + "args": { + "External id": 4727928,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894130.635, "dur": 35.017, + "args": { + "External id": 4727929,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894172.736, "dur": 48.610, + "args": { + "External id": 4727930,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894229.338, "dur": 28.049, + "args": { + "External id": 4727931,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894264.890, "dur": 43.810, + "args": { + "External id": 4727932,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359894335.142, "dur": 24.016, + "args": { + "External id": 4727933,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359894377.875, "dur": 28.147, + "args": { + "External id": 4727934,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359894425.946, "dur": 18.661, + "args": { + "External id": 4727935,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359894457.268, "dur": 14.178, + "args": { + "External id": 4727936,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894481.632, "dur": 27.212, + "args": { + "External id": 4727937,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894512.324, "dur": 35.368, + "args": { + "External id": 4727938,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359894575.761, "dur": 171.200, + "args": { + "External id": 4727939,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359894656.091, "dur": 6.111, + "args": { + "External id": 4727940,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359894664.120, "dur": 2.321, + "args": { + "External id": 4727941,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359894778.911, "dur": 22.178, + "args": { + "External id": 4727942,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359894813.135, "dur": 13.974, + "args": { + "External id": 4727943,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894835.379, "dur": 31.157, + "args": { + "External id": 4727944,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894873.140, "dur": 33.168, + "args": { + "External id": 4727945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894915.324, "dur": 20.637, + "args": { + "External id": 4727946,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894941.443, "dur": 29.275, + "args": { + "External id": 4727947,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359894977.328, "dur": 59.386, + "args": { + "External id": 4727948,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359895047.344, "dur": 60.853, + "args": { + "External id": 4727949,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359895140.008, "dur": 25.528, + "args": { + "External id": 4727950,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359895183.016, "dur": 24.002, + "args": { + "External id": 4727951,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359895221.836, "dur": 20.260, + "args": { + "External id": 4727952,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359895256.978, "dur": 14.035, + "args": { + "External id": 4727953,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359895286.368, "dur": 14.774, + "args": { + "External id": 4727954,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895376.956, "dur": 15.407, + "args": { + "External id": 4727955,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895380.380, "dur": 10.897, + "args": { + "External id": 4727956,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895384.460, "dur": 5.865, + "args": { + "External id": 4727957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895386.271, "dur": 3.930, + "args": { + "External id": 4727958,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895396.402, "dur": 10.112, + "args": { + "External id": 4727959,"Record function id": 0, "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895397.508, "dur": 8.588, + "args": { + "External id": 4727960,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895398.406, "dur": 7.147, + "args": { + "External id": 4727961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895399.433, "dur": 6.010, + "args": { + "External id": 4727962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895409.961, "dur": 5.297, + "args": { + "External id": 4727963,"Record function id": 0, "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895411.670, "dur": 3.179, + "args": { + "External id": 4727964,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895412.531, "dur": 1.721, + "args": { + "External id": 4727965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895413.151, "dur": 1.035, + "args": { + "External id": 4727966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895418.764, "dur": 4.126, + "args": { + "External id": 4727967,"Record function id": 0, "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895420.151, "dur": 2.326, + "args": { + "External id": 4727968,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895420.605, "dur": 1.416, + "args": { + "External id": 4727969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895421.286, "dur": 0.669, + "args": { + "External id": 4727970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895426.326, "dur": 4.007, + "args": { + "External id": 4727971,"Record function id": 0, "Ev Idx": 2722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895427.663, "dur": 2.276, + "args": { + "External id": 4727972,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895428.201, "dur": 1.308, + "args": { + "External id": 4727973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895428.785, "dur": 0.660, + "args": { + "External id": 4727974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895433.837, "dur": 4.311, + "args": { + "External id": 4727975,"Record function id": 0, "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895435.165, "dur": 2.593, + "args": { + "External id": 4727976,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895435.649, "dur": 1.536, + "args": { + "External id": 4727977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895436.372, "dur": 0.709, + "args": { + "External id": 4727978,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895441.764, "dur": 3.847, + "args": { + "External id": 4727979,"Record function id": 0, "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895443.011, "dur": 2.193, + "args": { + "External id": 4727980,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895443.481, "dur": 1.156, + "args": { + "External id": 4727981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895443.811, "dur": 0.740, + "args": { + "External id": 4727982,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895449.091, "dur": 4.161, + "args": { + "External id": 4727983,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895450.830, "dur": 2.010, + "args": { + "External id": 4727984,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895451.237, "dur": 1.007, + "args": { + "External id": 4727985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895451.528, "dur": 0.651, + "args": { + "External id": 4727986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895456.679, "dur": 5.831, + "args": { + "External id": 4727987,"Record function id": 0, "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359895457.918, "dur": 4.199, + "args": { + "External id": 4727988,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895458.555, "dur": 3.078, + "args": { + "External id": 4727989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359895459.097, "dur": 2.451, + "args": { + "External id": 4727990,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359895466.490, "dur": 37247.128, + "args": { + "External id": 4727991,"Record function id": 0, "Sequence number": 47018805, "Fwd thread id": 1, "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359895467.837, "dur": 37237.859, + "args": { + "External id": 4727992,"Sequence number": 47018805, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2743 + } + }, + { + "ph": "f", "id": 187, "pid": 1336753, "tid": 1381210, "ts": 1712359895467.837, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1712359895494.994, "dur": 36.093, + "args": { + "External id": 4727993,"Record function id": 0, "Ev Idx": 2744 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1712359895538.559, "dur": 60.809, + "args": { + "External id": 4727994,"Record function id": 0, "Ev Idx": 2745 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1712359895604.918, "dur": 37093.267, + "args": { + "External id": 4727995,"Record function id": 0, "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359895689.229, "dur": 6.207, + "args": { + "External id": 4727996,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359895704.573, "dur": 4.388, + "args": { + "External id": 4727997,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359895723.450, "dur": 36113.794, + "args": { + "External id": 4727998,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359895740.179, "dur": 36087.976, + "args": { + "External id": 4727999,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359895821.892, "dur": 13.236, + "args": { + "External id": 4728000,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359895841.507, "dur": 35947.426, + "args": { + "External id": 4728001,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359895844.524, "dur": 35943.381, + "args": { + "External id": 4728002,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359895848.811, "dur": 4.554, + "args": { + "External id": 4728003,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359895855.124, "dur": 35929.300, + "args": { + "External id": 4728004,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359931932.290, "dur": 9.384, + "args": { + "External id": 4728005,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359931935.649, "dur": 5.640, + "args": { + "External id": 4728006,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359931976.328, "dur": 423.931, + "args": { + "External id": 4728007,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359932042.148, "dur": 352.749, + "args": { + "External id": 4728008,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2759, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359932053.617, "dur": 335.218, + "args": { + "External id": 4728009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359932421.363, "dur": 2.583, + "args": { + "External id": 4728010,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2761, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932485.071, "dur": 6.642, + "args": { + "External id": 4728011,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932537.166, "dur": 3.531, + "args": { + "External id": 4728012,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932557.731, "dur": 0.972, + "args": { + "External id": 4728013,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932571.220, "dur": 0.876, + "args": { + "External id": 4728014,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932584.452, "dur": 1.061, + "args": { + "External id": 4728015,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932596.621, "dur": 2.676, + "args": { + "External id": 4728016,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932611.503, "dur": 0.871, + "args": { + "External id": 4728017,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932624.046, "dur": 1.886, + "args": { + "External id": 4728018,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932637.632, "dur": 0.847, + "args": { + "External id": 4728019,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359932727.881, "dur": 2704.081, + "args": { + "External id": 4728020,"Record function id": 0, "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1712359932746.915, "dur": 1019.875, + "args": { + "External id": 4728021,"Record function id": 0, "Ev Idx": 2772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1712359932760.760, "dur": 377.667, + "args": { + "External id": 4728022,"Record function id": 0, "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932840.933, "dur": 5.833, + "args": { + "External id": 4728023,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932849.761, "dur": 1.112, + "args": { + "External id": 4728024,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932852.803, "dur": 1.012, + "args": { + "External id": 4728025,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932855.675, "dur": 1.096, + "args": { + "External id": 4728026,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932858.520, "dur": 0.941, + "args": { + "External id": 4728027,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932866.796, "dur": 1.046, + "args": { + "External id": 4728028,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932869.683, "dur": 1.911, + "args": { + "External id": 4728029,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932873.117, "dur": 1.097, + "args": { + "External id": 4728030,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932875.669, "dur": 2.601, + "args": { + "External id": 4728031,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359932879.574, "dur": 0.983, + "args": { + "External id": 4728032,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359932897.021, "dur": 205.546, + "args": { + "External id": 4728033,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359932913.145, "dur": 184.187, + "args": { + "External id": 4728034,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359932930.665, "dur": 11.372, + "args": { + "External id": 4728035,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359932945.088, "dur": 107.751, + "args": { + "External id": 4728036,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359932948.034, "dur": 104.435, + "args": { + "External id": 4728037,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359932952.434, "dur": 5.309, + "args": { + "External id": 4728038,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359932959.870, "dur": 91.429, + "args": { + "External id": 4728039,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2790 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.18", "pid": 1336753, "tid": 1381210, + "ts": 1712359933229.870, "dur": 528.690, + "args": { + "External id": 4728040,"Record function id": 0, "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1712359933246.671, "dur": 499.732, + "args": { + "External id": 4728041,"Record function id": 0, "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359933308.547, "dur": 5.781, + "args": { + "External id": 4728042,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359933330.867, "dur": 31.220, + "args": { + "External id": 4728043,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933335.891, "dur": 1.663, + "args": { + "External id": 4728044,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933339.810, "dur": 0.781, + "args": { + "External id": 4728045,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933342.459, "dur": 0.455, + "args": { + "External id": 4728046,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933344.718, "dur": 2.548, + "args": { + "External id": 4728047,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933348.771, "dur": 0.530, + "args": { + "External id": 4728048,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933351.195, "dur": 0.315, + "args": { + "External id": 4728049,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933353.030, "dur": 0.388, + "args": { + "External id": 4728050,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933355.330, "dur": 0.507, + "args": { + "External id": 4728051,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933357.332, "dur": 0.419, + "args": { + "External id": 4728052,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359933372.160, "dur": 31.504, + "args": { + "External id": 4728053,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359933434.555, "dur": 107.546, + "args": { + "External id": 4728054,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359933444.322, "dur": 3.367, + "args": { + "External id": 4728055,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359933453.167, "dur": 13.619, + "args": { + "External id": 4728056,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359933457.688, "dur": 8.714, + "args": { + "External id": 4728057,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933461.389, "dur": 0.685, + "args": { + "External id": 4728058,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359933473.988, "dur": 28.102, + "args": { + "External id": 4728059,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933476.402, "dur": 2.387, + "args": { + "External id": 4728060,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933480.542, "dur": 0.395, + "args": { + "External id": 4728061,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933482.608, "dur": 0.453, + "args": { + "External id": 4728062,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933484.913, "dur": 0.699, + "args": { + "External id": 4728063,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933487.665, "dur": 0.494, + "args": { + "External id": 4728064,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933490.432, "dur": 0.413, + "args": { + "External id": 4728065,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933492.518, "dur": 0.347, + "args": { + "External id": 4728066,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933494.591, "dur": 0.386, + "args": { + "External id": 4728067,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359933496.600, "dur": 1.937, + "args": { + "External id": 4728068,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359933511.722, "dur": 23.173, + "args": { + "External id": 4728069,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359933583.699, "dur": 105.596, + "args": { + "External id": 4728070,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359933605.645, "dur": 80.510, + "args": { + "External id": 4728071,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2822, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359933614.621, "dur": 67.568, + "args": { + "External id": 4728072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359933701.642, "dur": 1.674, + "args": { + "External id": 4728073,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2824, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359933773.688, "dur": 1637.597, + "args": { + "External id": 4728074,"Sequence number": 47018804, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2825 + } + }, + { + "ph": "f", "id": 188, "pid": 1336753, "tid": 1381210, "ts": 1712359933773.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359933879.818, "dur": 97.827, + "args": { + "External id": 4728075,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359934059.817, "dur": 56.736, + "args": { + "External id": 4728076,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359934141.126, "dur": 57.464, + "args": { + "External id": 4728077,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359934208.796, "dur": 33.080, + "args": { + "External id": 4728078,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359934248.986, "dur": 47.030, + "args": { + "External id": 4728079,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359934303.377, "dur": 27.850, + "args": { + "External id": 4728080,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359934343.848, "dur": 42.061, + "args": { + "External id": 4728081,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359934412.914, "dur": 22.484, + "args": { + "External id": 4728082,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359934455.343, "dur": 27.259, + "args": { + "External id": 4728083,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359934502.663, "dur": 17.370, + "args": { + "External id": 4728084,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359934533.340, "dur": 14.518, + "args": { + "External id": 4728085,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359934560.203, "dur": 27.639, + "args": { + "External id": 4728086,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359934591.409, "dur": 32.998, + "args": { + "External id": 4728087,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359934651.514, "dur": 170.502, + "args": { + "External id": 4728088,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359934727.966, "dur": 5.928, + "args": { + "External id": 4728089,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359934735.646, "dur": 2.648, + "args": { + "External id": 4728090,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359934854.223, "dur": 25.582, + "args": { + "External id": 4728091,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359934890.701, "dur": 12.919, + "args": { + "External id": 4728092,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359934911.922, "dur": 31.590, + "args": { + "External id": 4728093,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359934952.331, "dur": 75.133, + "args": { + "External id": 4728094,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359935038.020, "dur": 24.947, + "args": { + "External id": 4728095,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359935083.864, "dur": 35.040, + "args": { + "External id": 4728096,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359935126.365, "dur": 19.705, + "args": { + "External id": 4728097,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359935155.275, "dur": 45.871, + "args": { + "External id": 4728098,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359935226.749, "dur": 22.524, + "args": { + "External id": 4728099,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359935266.709, "dur": 23.899, + "args": { + "External id": 4728100,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359935304.710, "dur": 16.227, + "args": { + "External id": 4728101,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359935335.422, "dur": 17.632, + "args": { + "External id": 4728102,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359935365.017, "dur": 14.771, + "args": { + "External id": 4728103,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935454.827, "dur": 16.948, + "args": { + "External id": 4728104,"Record function id": 0, "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935458.186, "dur": 12.663, + "args": { + "External id": 4728105,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935461.989, "dur": 7.931, + "args": { + "External id": 4728106,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935463.907, "dur": 5.900, + "args": { + "External id": 4728107,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935476.041, "dur": 4.802, + "args": { + "External id": 4728108,"Record function id": 0, "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935477.390, "dur": 3.043, + "args": { + "External id": 4728109,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935477.929, "dur": 1.996, + "args": { + "External id": 4728110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935478.706, "dur": 1.097, + "args": { + "External id": 4728111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935484.372, "dur": 4.699, + "args": { + "External id": 4728112,"Record function id": 0, "Ev Idx": 2863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935485.972, "dur": 2.697, + "args": { + "External id": 4728113,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935486.442, "dur": 1.759, + "args": { + "External id": 4728114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935487.126, "dur": 0.992, + "args": { + "External id": 4728115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935492.526, "dur": 4.003, + "args": { + "External id": 4728116,"Record function id": 0, "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935493.844, "dur": 2.291, + "args": { + "External id": 4728117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935494.454, "dur": 1.223, + "args": { + "External id": 4728118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935494.954, "dur": 0.663, + "args": { + "External id": 4728119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935499.811, "dur": 3.938, + "args": { + "External id": 4728120,"Record function id": 0, "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935500.872, "dur": 2.472, + "args": { + "External id": 4728121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935501.644, "dur": 1.305, + "args": { + "External id": 4728122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935502.113, "dur": 0.771, + "args": { + "External id": 4728123,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935507.216, "dur": 3.829, + "args": { + "External id": 4728124,"Record function id": 0, "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935508.284, "dur": 2.320, + "args": { + "External id": 4728125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935508.787, "dur": 1.242, + "args": { + "External id": 4728126,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935509.193, "dur": 0.731, + "args": { + "External id": 4728127,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935514.391, "dur": 3.285, + "args": { + "External id": 4728128,"Record function id": 0, "Ev Idx": 2879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935515.351, "dur": 1.916, + "args": { + "External id": 4728129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935515.843, "dur": 1.034, + "args": { + "External id": 4728130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935516.169, "dur": 0.644, + "args": { + "External id": 4728131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935521.066, "dur": 6.263, + "args": { + "External id": 4728132,"Record function id": 0, "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935522.185, "dur": 4.697, + "args": { + "External id": 4728133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935522.676, "dur": 3.740, + "args": { + "External id": 4728134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935523.322, "dur": 3.034, + "args": { + "External id": 4728135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935530.765, "dur": 4.119, + "args": { + "External id": 4728136,"Record function id": 0, "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359935531.927, "dur": 2.548, + "args": { + "External id": 4728137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935532.390, "dur": 1.497, + "args": { + "External id": 4728138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359935532.990, "dur": 0.814, + "args": { + "External id": 4728139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359935539.068, "dur": 38995.244, + "args": { + "External id": 4728140,"Record function id": 0, "Sequence number": 47018803, "Fwd thread id": 1, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359935540.284, "dur": 38986.091, + "args": { + "External id": 4728141,"Sequence number": 47018803, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2892 + } + }, + { + "ph": "f", "id": 189, "pid": 1336753, "tid": 1381210, "ts": 1712359935540.284, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1712359935567.966, "dur": 36.533, + "args": { + "External id": 4728142,"Record function id": 0, "Ev Idx": 2893 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1712359935612.488, "dur": 64.595, + "args": { + "External id": 4728143,"Record function id": 0, "Ev Idx": 2894 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1712359935682.534, "dur": 38835.421, + "args": { + "External id": 4728144,"Record function id": 0, "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359935769.137, "dur": 6.327, + "args": { + "External id": 4728145,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359935785.160, "dur": 4.343, + "args": { + "External id": 4728146,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359935804.809, "dur": 37801.697, + "args": { + "External id": 4728147,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359935818.087, "dur": 37778.081, + "args": { + "External id": 4728148,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359935913.290, "dur": 14.198, + "args": { + "External id": 4728149,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359935933.736, "dur": 37623.576, + "args": { + "External id": 4728150,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359935936.296, "dur": 37620.111, + "args": { + "External id": 4728151,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359935940.810, "dur": 5.180, + "args": { + "External id": 4728152,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359935948.230, "dur": 37604.323, + "args": { + "External id": 4728153,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359973704.973, "dur": 10.538, + "args": { + "External id": 4728154,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359973709.006, "dur": 6.222, + "args": { + "External id": 4728155,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359973749.452, "dur": 461.886, + "args": { + "External id": 4728156,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359973776.136, "dur": 428.961, + "args": { + "External id": 4728157,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2908, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359973787.121, "dur": 411.869, + "args": { + "External id": 4728158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359974233.811, "dur": 2.898, + "args": { + "External id": 4728159,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2910, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974302.052, "dur": 7.286, + "args": { + "External id": 4728160,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974355.990, "dur": 1.426, + "args": { + "External id": 4728161,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974373.763, "dur": 0.880, + "args": { + "External id": 4728162,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974386.324, "dur": 0.882, + "args": { + "External id": 4728163,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974398.819, "dur": 0.854, + "args": { + "External id": 4728164,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974413.924, "dur": 0.836, + "args": { + "External id": 4728165,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974426.626, "dur": 0.751, + "args": { + "External id": 4728166,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974439.244, "dur": 1.851, + "args": { + "External id": 4728167,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974452.646, "dur": 1.023, + "args": { + "External id": 4728168,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359974550.507, "dur": 2759.960, + "args": { + "External id": 4728169,"Record function id": 0, "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1712359974569.387, "dur": 1057.545, + "args": { + "External id": 4728170,"Record function id": 0, "Ev Idx": 2921 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1712359974584.259, "dur": 316.735, + "args": { + "External id": 4728171,"Record function id": 0, "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974667.574, "dur": 4.064, + "args": { + "External id": 4728172,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974675.145, "dur": 1.340, + "args": { + "External id": 4728173,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974678.337, "dur": 1.484, + "args": { + "External id": 4728174,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974682.008, "dur": 1.153, + "args": { + "External id": 4728175,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974684.782, "dur": 0.966, + "args": { + "External id": 4728176,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974687.513, "dur": 1.371, + "args": { + "External id": 4728177,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974690.545, "dur": 1.830, + "args": { + "External id": 4728178,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974693.718, "dur": 2.719, + "args": { + "External id": 4728179,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974697.991, "dur": 0.815, + "args": { + "External id": 4728180,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359974700.751, "dur": 0.684, + "args": { + "External id": 4728181,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359974719.298, "dur": 150.607, + "args": { + "External id": 4728182,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359974735.045, "dur": 130.790, + "args": { + "External id": 4728183,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359974759.363, "dur": 11.984, + "args": { + "External id": 4728184,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359974774.471, "dur": 64.243, + "args": { + "External id": 4728185,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359974777.189, "dur": 61.230, + "args": { + "External id": 4728186,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359974781.355, "dur": 5.091, + "args": { + "External id": 4728187,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359974788.363, "dur": 49.427, + "args": { + "External id": 4728188,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2939 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.17", "pid": 1336753, "tid": 1381210, + "ts": 1712359975034.236, "dur": 582.911, + "args": { + "External id": 4728189,"Record function id": 0, "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1712359975053.117, "dur": 550.473, + "args": { + "External id": 4728190,"Record function id": 0, "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359975135.925, "dur": 6.833, + "args": { + "External id": 4728191,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359975159.578, "dur": 35.727, + "args": { + "External id": 4728192,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975164.745, "dur": 1.549, + "args": { + "External id": 4728193,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975168.590, "dur": 0.898, + "args": { + "External id": 4728194,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975171.268, "dur": 2.648, + "args": { + "External id": 4728195,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975175.940, "dur": 0.462, + "args": { + "External id": 4728196,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975177.925, "dur": 0.525, + "args": { + "External id": 4728197,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975180.000, "dur": 0.446, + "args": { + "External id": 4728198,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975186.129, "dur": 0.426, + "args": { + "External id": 4728199,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975188.210, "dur": 0.364, + "args": { + "External id": 4728200,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975190.296, "dur": 0.411, + "args": { + "External id": 4728201,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359975205.315, "dur": 36.546, + "args": { + "External id": 4728202,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712359975278.561, "dur": 106.668, + "args": { + "External id": 4728203,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359975288.933, "dur": 3.611, + "args": { + "External id": 4728204,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712359975297.803, "dur": 11.613, + "args": { + "External id": 4728205,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712359975302.064, "dur": 6.965, + "args": { + "External id": 4728206,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975305.750, "dur": 2.112, + "args": { + "External id": 4728207,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712359975316.284, "dur": 27.164, + "args": { + "External id": 4728208,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975318.624, "dur": 0.430, + "args": { + "External id": 4728209,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975320.691, "dur": 0.304, + "args": { + "External id": 4728210,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975322.660, "dur": 0.375, + "args": { + "External id": 4728211,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975324.598, "dur": 0.360, + "args": { + "External id": 4728212,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975329.771, "dur": 0.282, + "args": { + "External id": 4728213,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975331.581, "dur": 0.332, + "args": { + "External id": 4728214,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975333.496, "dur": 0.493, + "args": { + "External id": 4728215,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975335.660, "dur": 2.047, + "args": { + "External id": 4728216,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359975339.470, "dur": 0.388, + "args": { + "External id": 4728217,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359975358.255, "dur": 19.817, + "args": { + "External id": 4728218,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712359975430.537, "dur": 108.781, + "args": { + "External id": 4728219,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359975454.997, "dur": 80.789, + "args": { + "External id": 4728220,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2971, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712359975464.803, "dur": 66.488, + "args": { + "External id": 4728221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712359975555.690, "dur": 2.058, + "args": { + "External id": 4728222,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2973, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359975633.966, "dur": 1655.338, + "args": { + "External id": 4728223,"Sequence number": 47018802, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2974 + } + }, + { + "ph": "f", "id": 190, "pid": 1336753, "tid": 1381210, "ts": 1712359975633.966, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359975740.768, "dur": 96.994, + "args": { + "External id": 4728224,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359975872.752, "dur": 37.235, + "args": { + "External id": 4728225,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712359975930.158, "dur": 47.930, + "args": { + "External id": 4728226,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976034.648, "dur": 54.836, + "args": { + "External id": 4728227,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976100.350, "dur": 49.545, + "args": { + "External id": 4728228,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976158.304, "dur": 27.700, + "args": { + "External id": 4728229,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976195.484, "dur": 42.826, + "args": { + "External id": 4728230,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359976263.529, "dur": 27.948, + "args": { + "External id": 4728231,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712359976310.356, "dur": 26.906, + "args": { + "External id": 4728232,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359976357.933, "dur": 18.799, + "args": { + "External id": 4728233,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359976389.620, "dur": 15.200, + "args": { + "External id": 4728234,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976416.600, "dur": 27.761, + "args": { + "External id": 4728235,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976447.488, "dur": 34.882, + "args": { + "External id": 4728236,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712359976509.514, "dur": 170.087, + "args": { + "External id": 4728237,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359976585.372, "dur": 6.371, + "args": { + "External id": 4728238,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359976593.862, "dur": 2.347, + "args": { + "External id": 4728239,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359976711.074, "dur": 25.104, + "args": { + "External id": 4728240,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712359976747.202, "dur": 13.923, + "args": { + "External id": 4728241,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976771.589, "dur": 34.466, + "args": { + "External id": 4728242,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976813.196, "dur": 35.571, + "args": { + "External id": 4728243,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976856.164, "dur": 20.315, + "args": { + "External id": 4728244,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976881.884, "dur": 29.452, + "args": { + "External id": 4728245,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976919.003, "dur": 19.759, + "args": { + "External id": 4728246,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712359976945.788, "dur": 98.493, + "args": { + "External id": 4728247,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712359977091.754, "dur": 25.971, + "args": { + "External id": 4728248,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359977139.599, "dur": 24.364, + "args": { + "External id": 4728249,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712359977179.214, "dur": 19.801, + "args": { + "External id": 4728250,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712359977215.039, "dur": 14.121, + "args": { + "External id": 4728251,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712359977241.613, "dur": 18.554, + "args": { + "External id": 4728252,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977332.620, "dur": 14.822, + "args": { + "External id": 4728253,"Record function id": 0, "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977335.666, "dur": 10.828, + "args": { + "External id": 4728254,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977339.509, "dur": 6.078, + "args": { + "External id": 4728255,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977341.468, "dur": 3.987, + "args": { + "External id": 4728256,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977351.347, "dur": 5.527, + "args": { + "External id": 4728257,"Record function id": 0, "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977352.583, "dur": 3.842, + "args": { + "External id": 4728258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977353.829, "dur": 2.105, + "args": { + "External id": 4728259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977354.568, "dur": 1.246, + "args": { + "External id": 4728260,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977360.469, "dur": 5.245, + "args": { + "External id": 4728261,"Record function id": 0, "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977361.709, "dur": 3.616, + "args": { + "External id": 4728262,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977362.822, "dur": 1.795, + "args": { + "External id": 4728263,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977363.321, "dur": 1.218, + "args": { + "External id": 4728264,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977369.038, "dur": 4.169, + "args": { + "External id": 4728265,"Record function id": 0, "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977370.460, "dur": 2.369, + "args": { + "External id": 4728266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977370.934, "dur": 1.378, + "args": { + "External id": 4728267,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977371.416, "dur": 0.821, + "args": { + "External id": 4728268,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977376.391, "dur": 3.790, + "args": { + "External id": 4728269,"Record function id": 0, "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977377.893, "dur": 1.892, + "args": { + "External id": 4728270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977378.362, "dur": 1.016, + "args": { + "External id": 4728271,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977378.698, "dur": 0.614, + "args": { + "External id": 4728272,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977383.526, "dur": 3.990, + "args": { + "External id": 4728273,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977384.634, "dur": 2.500, + "args": { + "External id": 4728274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977385.145, "dur": 1.419, + "args": { + "External id": 4728275,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977385.689, "dur": 0.776, + "args": { + "External id": 4728276,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977390.800, "dur": 6.389, + "args": { + "External id": 4728277,"Record function id": 0, "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977392.160, "dur": 4.593, + "args": { + "External id": 4728278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977392.982, "dur": 3.349, + "args": { + "External id": 4728279,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977393.276, "dur": 2.976, + "args": { + "External id": 4728280,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977400.459, "dur": 4.664, + "args": { + "External id": 4728281,"Record function id": 0, "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977402.099, "dur": 2.646, + "args": { + "External id": 4728282,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977402.912, "dur": 1.262, + "args": { + "External id": 4728283,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977403.385, "dur": 0.702, + "args": { + "External id": 4728284,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977408.378, "dur": 4.478, + "args": { + "External id": 4728285,"Record function id": 0, "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712359977409.854, "dur": 2.606, + "args": { + "External id": 4728286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977410.486, "dur": 1.297, + "args": { + "External id": 4728287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712359977411.136, "dur": 0.559, + "args": { + "External id": 4728288,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359977417.116, "dur": 37396.374, + "args": { + "External id": 4728289,"Record function id": 0, "Sequence number": 47018801, "Fwd thread id": 1, "Ev Idx": 3040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712359977418.490, "dur": 37386.413, + "args": { + "External id": 4728290,"Sequence number": 47018801, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3041 + } + }, + { + "ph": "f", "id": 191, "pid": 1336753, "tid": 1381210, "ts": 1712359977418.490, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1712359977446.367, "dur": 36.469, + "args": { + "External id": 4728291,"Record function id": 0, "Ev Idx": 3042 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1712359977490.768, "dur": 64.744, + "args": { + "External id": 4728292,"Record function id": 0, "Ev Idx": 3043 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1712359977561.559, "dur": 37235.631, + "args": { + "External id": 4728293,"Record function id": 0, "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359977648.043, "dur": 6.220, + "args": { + "External id": 4728294,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712359977663.396, "dur": 4.962, + "args": { + "External id": 4728295,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359977682.966, "dur": 36292.184, + "args": { + "External id": 4728296,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712359977760.974, "dur": 36204.542, + "args": { + "External id": 4728297,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712359977810.951, "dur": 13.657, + "args": { + "External id": 4728298,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712359977831.015, "dur": 36094.075, + "args": { + "External id": 4728299,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712359977833.724, "dur": 36090.576, + "args": { + "External id": 4728300,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712359977838.008, "dur": 6.138, + "args": { + "External id": 4728301,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712359977846.382, "dur": 36074.368, + "args": { + "External id": 4728302,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360014106.137, "dur": 10.383, + "args": { + "External id": 4728303,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360014109.856, "dur": 6.091, + "args": { + "External id": 4728304,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360014146.959, "dur": 355.201, + "args": { + "External id": 4728305,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360014173.584, "dur": 323.614, + "args": { + "External id": 4728306,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3057, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360014184.820, "dur": 306.356, + "args": { + "External id": 4728307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360014520.212, "dur": 2.597, + "args": { + "External id": 4728308,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3059, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360014578.769, "dur": 8.678, + "args": { + "External id": 4728309,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360014631.812, "dur": 1.487, + "args": { + "External id": 4728310,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360014651.229, "dur": 1.006, + "args": { + "External id": 4728311,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360014666.410, "dur": 1.118, + "args": { + "External id": 4728312,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360014679.219, "dur": 2.420, + "args": { + "External id": 4728313,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360014693.515, "dur": 1.069, + "args": { + "External id": 4728314,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360014706.919, "dur": 1.269, + "args": { + "External id": 4728315,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360014720.641, "dur": 2.345, + "args": { + "External id": 4728316,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360014734.420, "dur": 2.796, + "args": { + "External id": 4728317,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360014828.612, "dur": 2826.815, + "args": { + "External id": 4728318,"Record function id": 0, "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1712360014848.027, "dur": 1125.841, + "args": { + "External id": 4728319,"Record function id": 0, "Ev Idx": 3070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1712360014863.319, "dur": 458.176, + "args": { + "External id": 4728320,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015059.977, "dur": 19.925, + "args": { + "External id": 4728321,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015086.852, "dur": 1.436, + "args": { + "External id": 4728322,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015090.387, "dur": 1.133, + "args": { + "External id": 4728323,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015093.114, "dur": 1.085, + "args": { + "External id": 4728324,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015096.229, "dur": 0.758, + "args": { + "External id": 4728325,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015099.927, "dur": 0.969, + "args": { + "External id": 4728326,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015102.698, "dur": 3.510, + "args": { + "External id": 4728327,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015107.754, "dur": 1.093, + "args": { + "External id": 4728328,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015110.416, "dur": 1.039, + "args": { + "External id": 4728329,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360015112.980, "dur": 0.785, + "args": { + "External id": 4728330,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360015133.767, "dur": 152.682, + "args": { + "External id": 4728331,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360015150.869, "dur": 130.644, + "args": { + "External id": 4728332,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360015171.132, "dur": 11.792, + "args": { + "External id": 4728333,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360015186.089, "dur": 68.445, + "args": { + "External id": 4728334,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360015188.738, "dur": 65.545, + "args": { + "External id": 4728335,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015192.975, "dur": 6.059, + "args": { + "External id": 4728336,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360015201.042, "dur": 52.653, + "args": { + "External id": 4728337,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3088 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.16", "pid": 1336753, "tid": 1381210, + "ts": 1712360015417.430, "dur": 547.056, + "args": { + "External id": 4728338,"Record function id": 0, "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1712360015436.466, "dur": 514.724, + "args": { + "External id": 4728339,"Record function id": 0, "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360015500.186, "dur": 4.971, + "args": { + "External id": 4728340,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360015520.431, "dur": 30.464, + "args": { + "External id": 4728341,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015525.421, "dur": 1.468, + "args": { + "External id": 4728342,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015528.959, "dur": 2.517, + "args": { + "External id": 4728343,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015533.207, "dur": 0.425, + "args": { + "External id": 4728344,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015535.118, "dur": 0.651, + "args": { + "External id": 4728345,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015537.322, "dur": 0.513, + "args": { + "External id": 4728346,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015539.834, "dur": 0.406, + "args": { + "External id": 4728347,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015542.031, "dur": 0.320, + "args": { + "External id": 4728348,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015543.961, "dur": 0.548, + "args": { + "External id": 4728349,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015546.273, "dur": 0.454, + "args": { + "External id": 4728350,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360015560.159, "dur": 31.673, + "args": { + "External id": 4728351,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360015621.846, "dur": 105.599, + "args": { + "External id": 4728352,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360015631.710, "dur": 5.381, + "args": { + "External id": 4728353,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360015642.142, "dur": 10.152, + "args": { + "External id": 4728354,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360015646.266, "dur": 5.613, + "args": { + "External id": 4728355,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015650.106, "dur": 0.632, + "args": { + "External id": 4728356,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360015659.107, "dur": 24.946, + "args": { + "External id": 4728357,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015661.049, "dur": 0.435, + "args": { + "External id": 4728358,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015663.147, "dur": 0.403, + "args": { + "External id": 4728359,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015665.097, "dur": 0.427, + "args": { + "External id": 4728360,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015667.084, "dur": 0.409, + "args": { + "External id": 4728361,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015669.236, "dur": 0.627, + "args": { + "External id": 4728362,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015671.719, "dur": 0.524, + "args": { + "External id": 4728363,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015674.070, "dur": 2.574, + "args": { + "External id": 4728364,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015678.267, "dur": 0.533, + "args": { + "External id": 4728365,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360015680.479, "dur": 0.592, + "args": { + "External id": 4728366,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360015699.466, "dur": 21.204, + "args": { + "External id": 4728367,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360015771.794, "dur": 114.035, + "args": { + "External id": 4728368,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360015796.589, "dur": 85.472, + "args": { + "External id": 4728369,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3120, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360015806.185, "dur": 71.586, + "args": { + "External id": 4728370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360015901.416, "dur": 1.915, + "args": { + "External id": 4728371,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3122, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360016027.624, "dur": 1606.761, + "args": { + "External id": 4728372,"Sequence number": 47018800, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3123 + } + }, + { + "ph": "f", "id": 192, "pid": 1336753, "tid": 1381210, "ts": 1712360016027.624, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360016163.009, "dur": 102.834, + "args": { + "External id": 4728373,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360016304.377, "dur": 39.276, + "args": { + "External id": 4728374,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360016364.257, "dur": 46.835, + "args": { + "External id": 4728375,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360016420.603, "dur": 31.309, + "args": { + "External id": 4728376,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360016459.228, "dur": 45.700, + "args": { + "External id": 4728377,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360016514.488, "dur": 29.417, + "args": { + "External id": 4728378,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360016551.843, "dur": 45.152, + "args": { + "External id": 4728379,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360016618.313, "dur": 20.492, + "args": { + "External id": 4728380,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360016655.722, "dur": 27.263, + "args": { + "External id": 4728381,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360016702.568, "dur": 18.352, + "args": { + "External id": 4728382,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360016733.026, "dur": 14.526, + "args": { + "External id": 4728383,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360016758.800, "dur": 27.763, + "args": { + "External id": 4728384,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360016789.834, "dur": 32.249, + "args": { + "External id": 4728385,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360016847.383, "dur": 208.278, + "args": { + "External id": 4728386,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360016921.211, "dur": 5.335, + "args": { + "External id": 4728387,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360016928.759, "dur": 3.994, + "args": { + "External id": 4728388,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360017108.863, "dur": 28.196, + "args": { + "External id": 4728389,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360017164.233, "dur": 14.934, + "args": { + "External id": 4728390,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360017189.927, "dur": 41.320, + "args": { + "External id": 4728391,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360017237.980, "dur": 35.573, + "args": { + "External id": 4728392,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360017280.814, "dur": 35.784, + "args": { + "External id": 4728393,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360017328.923, "dur": 35.339, + "args": { + "External id": 4728394,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360017371.892, "dur": 20.114, + "args": { + "External id": 4728395,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360017402.852, "dur": 28.545, + "args": { + "External id": 4728396,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360017450.114, "dur": 25.083, + "args": { + "External id": 4728397,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360017491.616, "dur": 23.360, + "args": { + "External id": 4728398,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360017532.215, "dur": 16.179, + "args": { + "External id": 4728399,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360017561.914, "dur": 17.188, + "args": { + "External id": 4728400,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360017591.952, "dur": 15.292, + "args": { + "External id": 4728401,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017677.975, "dur": 14.432, + "args": { + "External id": 4728402,"Record function id": 0, "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017681.163, "dur": 10.264, + "args": { + "External id": 4728403,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017684.995, "dur": 5.576, + "args": { + "External id": 4728404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017686.540, "dur": 3.906, + "args": { + "External id": 4728405,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017696.431, "dur": 5.137, + "args": { + "External id": 4728406,"Record function id": 0, "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017697.713, "dur": 3.441, + "args": { + "External id": 4728407,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017698.270, "dur": 2.426, + "args": { + "External id": 4728408,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017699.426, "dur": 1.159, + "args": { + "External id": 4728409,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017705.275, "dur": 3.920, + "args": { + "External id": 4728410,"Record function id": 0, "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017706.379, "dur": 2.414, + "args": { + "External id": 4728411,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017706.996, "dur": 1.350, + "args": { + "External id": 4728412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017707.346, "dur": 0.923, + "args": { + "External id": 4728413,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017712.387, "dur": 5.832, + "args": { + "External id": 4728414,"Record function id": 0, "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017713.491, "dur": 4.344, + "args": { + "External id": 4728415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017714.156, "dur": 3.016, + "args": { + "External id": 4728416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017714.766, "dur": 2.310, + "args": { + "External id": 4728417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017721.356, "dur": 3.876, + "args": { + "External id": 4728418,"Record function id": 0, "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017722.765, "dur": 2.049, + "args": { + "External id": 4728419,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017723.249, "dur": 1.148, + "args": { + "External id": 4728420,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017723.675, "dur": 0.658, + "args": { + "External id": 4728421,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017728.428, "dur": 3.551, + "args": { + "External id": 4728422,"Record function id": 0, "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017729.510, "dur": 2.061, + "args": { + "External id": 4728423,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017729.935, "dur": 1.197, + "args": { + "External id": 4728424,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017730.390, "dur": 0.642, + "args": { + "External id": 4728425,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017735.212, "dur": 3.243, + "args": { + "External id": 4728426,"Record function id": 0, "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017736.150, "dur": 1.868, + "args": { + "External id": 4728427,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017736.579, "dur": 1.023, + "args": { + "External id": 4728428,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017736.866, "dur": 0.625, + "args": { + "External id": 4728429,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017741.553, "dur": 3.418, + "args": { + "External id": 4728430,"Record function id": 0, "Ev Idx": 3181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017742.621, "dur": 1.930, + "args": { + "External id": 4728431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017743.071, "dur": 0.870, + "args": { + "External id": 4728432,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017743.346, "dur": 0.530, + "args": { + "External id": 4728433,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017748.133, "dur": 3.741, + "args": { + "External id": 4728434,"Record function id": 0, "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360017749.167, "dur": 2.310, + "args": { + "External id": 4728435,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017749.594, "dur": 1.446, + "args": { + "External id": 4728436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360017750.295, "dur": 0.658, + "args": { + "External id": 4728437,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360017755.753, "dur": 38644.188, + "args": { + "External id": 4728438,"Record function id": 0, "Sequence number": 47018799, "Fwd thread id": 1, "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360017757.229, "dur": 38634.678, + "args": { + "External id": 4728439,"Sequence number": 47018799, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3190 + } + }, + { + "ph": "f", "id": 193, "pid": 1336753, "tid": 1381210, "ts": 1712360017757.229, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1712360017785.749, "dur": 35.215, + "args": { + "External id": 4728440,"Record function id": 0, "Ev Idx": 3191 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1712360017828.652, "dur": 62.117, + "args": { + "External id": 4728441,"Record function id": 0, "Ev Idx": 3192 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1712360017896.588, "dur": 38488.339, + "args": { + "External id": 4728442,"Record function id": 0, "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360018018.709, "dur": 8.506, + "args": { + "External id": 4728443,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360018039.513, "dur": 5.128, + "args": { + "External id": 4728444,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360018079.188, "dur": 37406.062, + "args": { + "External id": 4728445,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360018094.629, "dur": 37381.657, + "args": { + "External id": 4728446,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360018156.134, "dur": 16.080, + "args": { + "External id": 4728447,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360018181.921, "dur": 37255.511, + "args": { + "External id": 4728448,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360018184.673, "dur": 37252.038, + "args": { + "External id": 4728449,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360018189.416, "dur": 5.727, + "args": { + "External id": 4728450,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360018197.094, "dur": 37235.863, + "args": { + "External id": 4728451,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360055577.601, "dur": 9.130, + "args": { + "External id": 4728452,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360055580.961, "dur": 5.397, + "args": { + "External id": 4728453,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360055621.392, "dur": 458.215, + "args": { + "External id": 4728454,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360055647.543, "dur": 414.202, + "args": { + "External id": 4728455,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3206, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360055658.529, "dur": 396.931, + "args": { + "External id": 4728456,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360056102.655, "dur": 3.152, + "args": { + "External id": 4728457,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3208, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056167.841, "dur": 7.167, + "args": { + "External id": 4728458,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056219.873, "dur": 1.156, + "args": { + "External id": 4728459,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056241.504, "dur": 1.155, + "args": { + "External id": 4728460,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056257.692, "dur": 1.016, + "args": { + "External id": 4728461,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056270.619, "dur": 1.024, + "args": { + "External id": 4728462,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056282.316, "dur": 1.103, + "args": { + "External id": 4728463,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056295.124, "dur": 0.961, + "args": { + "External id": 4728464,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056310.996, "dur": 1.844, + "args": { + "External id": 4728465,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056324.318, "dur": 0.791, + "args": { + "External id": 4728466,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360056416.884, "dur": 2720.712, + "args": { + "External id": 4728467,"Record function id": 0, "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1712360056435.355, "dur": 1034.089, + "args": { + "External id": 4728468,"Record function id": 0, "Ev Idx": 3219 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1712360056452.567, "dur": 316.766, + "args": { + "External id": 4728469,"Record function id": 0, "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056533.235, "dur": 4.095, + "args": { + "External id": 4728470,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056540.427, "dur": 1.534, + "args": { + "External id": 4728471,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056543.675, "dur": 1.346, + "args": { + "External id": 4728472,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056546.480, "dur": 2.833, + "args": { + "External id": 4728473,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056550.898, "dur": 1.018, + "args": { + "External id": 4728474,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056554.024, "dur": 1.013, + "args": { + "External id": 4728475,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056556.732, "dur": 1.635, + "args": { + "External id": 4728476,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056559.772, "dur": 1.105, + "args": { + "External id": 4728477,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056562.333, "dur": 0.866, + "args": { + "External id": 4728478,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360056564.726, "dur": 0.750, + "args": { + "External id": 4728479,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360056582.949, "dur": 156.657, + "args": { + "External id": 4728480,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360056599.197, "dur": 135.899, + "args": { + "External id": 4728481,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360056624.197, "dur": 12.239, + "args": { + "External id": 4728482,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360056639.546, "dur": 68.223, + "args": { + "External id": 4728483,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360056642.234, "dur": 65.088, + "args": { + "External id": 4728484,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056646.418, "dur": 6.990, + "args": { + "External id": 4728485,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360056655.247, "dur": 51.542, + "args": { + "External id": 4728486,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3237 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.15", "pid": 1336753, "tid": 1381210, + "ts": 1712360056860.539, "dur": 600.310, + "args": { + "External id": 4728487,"Record function id": 0, "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1712360056875.070, "dur": 572.783, + "args": { + "External id": 4728488,"Record function id": 0, "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360056931.016, "dur": 4.531, + "args": { + "External id": 4728489,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360056950.812, "dur": 29.374, + "args": { + "External id": 4728490,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056955.520, "dur": 1.156, + "args": { + "External id": 4728491,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056958.817, "dur": 0.529, + "args": { + "External id": 4728492,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056960.863, "dur": 0.452, + "args": { + "External id": 4728493,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056963.095, "dur": 0.486, + "args": { + "External id": 4728494,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056965.203, "dur": 0.475, + "args": { + "External id": 4728495,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056967.321, "dur": 0.383, + "args": { + "External id": 4728496,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056969.808, "dur": 2.278, + "args": { + "External id": 4728497,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056973.935, "dur": 0.364, + "args": { + "External id": 4728498,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360056976.043, "dur": 0.409, + "args": { + "External id": 4728499,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360057031.839, "dur": 51.801, + "args": { + "External id": 4728500,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360057120.220, "dur": 112.811, + "args": { + "External id": 4728501,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360057131.375, "dur": 4.797, + "args": { + "External id": 4728502,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360057141.492, "dur": 10.366, + "args": { + "External id": 4728503,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360057145.448, "dur": 5.947, + "args": { + "External id": 4728504,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057149.384, "dur": 0.615, + "args": { + "External id": 4728505,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360057159.602, "dur": 29.339, + "args": { + "External id": 4728506,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057161.998, "dur": 0.511, + "args": { + "External id": 4728507,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057167.367, "dur": 0.435, + "args": { + "External id": 4728508,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057169.507, "dur": 0.402, + "args": { + "External id": 4728509,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057171.412, "dur": 2.432, + "args": { + "External id": 4728510,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057175.947, "dur": 0.352, + "args": { + "External id": 4728511,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057177.995, "dur": 0.360, + "args": { + "External id": 4728512,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057180.303, "dur": 0.392, + "args": { + "External id": 4728513,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057182.167, "dur": 0.342, + "args": { + "External id": 4728514,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360057184.370, "dur": 0.383, + "args": { + "External id": 4728515,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360057201.314, "dur": 24.538, + "args": { + "External id": 4728516,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360057279.764, "dur": 107.160, + "args": { + "External id": 4728517,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360057301.888, "dur": 81.710, + "args": { + "External id": 4728518,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3269, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360057311.308, "dur": 68.421, + "args": { + "External id": 4728519,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360057400.128, "dur": 1.888, + "args": { + "External id": 4728520,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3271, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360057476.957, "dur": 1638.881, + "args": { + "External id": 4728521,"Sequence number": 47018798, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3272 + } + }, + { + "ph": "f", "id": 194, "pid": 1336753, "tid": 1381210, "ts": 1712360057476.957, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360057584.069, "dur": 103.691, + "args": { + "External id": 4728522,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360057724.734, "dur": 36.399, + "args": { + "External id": 4728523,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360057778.548, "dur": 48.973, + "args": { + "External id": 4728524,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360057836.968, "dur": 32.015, + "args": { + "External id": 4728525,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360057877.051, "dur": 45.500, + "args": { + "External id": 4728526,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360057945.399, "dur": 29.249, + "args": { + "External id": 4728527,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360058025.163, "dur": 63.960, + "args": { + "External id": 4728528,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360058121.729, "dur": 24.806, + "args": { + "External id": 4728529,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360058169.303, "dur": 28.195, + "args": { + "External id": 4728530,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360058218.341, "dur": 19.170, + "args": { + "External id": 4728531,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360058251.436, "dur": 14.660, + "args": { + "External id": 4728532,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360058276.368, "dur": 31.604, + "args": { + "External id": 4728533,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360058311.621, "dur": 33.255, + "args": { + "External id": 4728534,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360058372.437, "dur": 172.600, + "args": { + "External id": 4728535,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360058448.265, "dur": 5.951, + "args": { + "External id": 4728536,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360058456.433, "dur": 2.157, + "args": { + "External id": 4728537,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360058576.007, "dur": 25.561, + "args": { + "External id": 4728538,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360058613.204, "dur": 13.752, + "args": { + "External id": 4728539,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360058634.676, "dur": 31.598, + "args": { + "External id": 4728540,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360058673.192, "dur": 34.226, + "args": { + "External id": 4728541,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360058716.243, "dur": 20.443, + "args": { + "External id": 4728542,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360058742.161, "dur": 29.499, + "args": { + "External id": 4728543,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360058777.626, "dur": 19.714, + "args": { + "External id": 4728544,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360058804.680, "dur": 28.944, + "args": { + "External id": 4728545,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360058848.951, "dur": 20.549, + "args": { + "External id": 4728546,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360058901.017, "dur": 29.231, + "args": { + "External id": 4728547,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360058944.178, "dur": 15.513, + "args": { + "External id": 4728548,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360058976.129, "dur": 53.281, + "args": { + "External id": 4728549,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360059049.922, "dur": 31.965, + "args": { + "External id": 4728550,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059161.557, "dur": 15.439, + "args": { + "External id": 4728551,"Record function id": 0, "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059164.866, "dur": 11.270, + "args": { + "External id": 4728552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059168.977, "dur": 5.997, + "args": { + "External id": 4728553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059170.727, "dur": 4.127, + "args": { + "External id": 4728554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059181.161, "dur": 5.873, + "args": { + "External id": 4728555,"Record function id": 0, "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059182.679, "dur": 3.916, + "args": { + "External id": 4728556,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059183.779, "dur": 2.311, + "args": { + "External id": 4728557,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059184.766, "dur": 1.200, + "args": { + "External id": 4728558,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059190.429, "dur": 6.957, + "args": { + "External id": 4728559,"Record function id": 0, "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059191.768, "dur": 5.220, + "args": { + "External id": 4728560,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059192.684, "dur": 3.868, + "args": { + "External id": 4728561,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059193.256, "dur": 3.215, + "args": { + "External id": 4728562,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059200.900, "dur": 4.111, + "args": { + "External id": 4728563,"Record function id": 0, "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059202.261, "dur": 2.350, + "args": { + "External id": 4728564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059202.832, "dur": 1.376, + "args": { + "External id": 4728565,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059203.317, "dur": 0.824, + "args": { + "External id": 4728566,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059208.587, "dur": 3.917, + "args": { + "External id": 4728567,"Record function id": 0, "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059209.739, "dur": 2.315, + "args": { + "External id": 4728568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059210.636, "dur": 1.010, + "args": { + "External id": 4728569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059210.939, "dur": 0.638, + "args": { + "External id": 4728570,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059215.768, "dur": 4.828, + "args": { + "External id": 4728571,"Record function id": 0, "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059217.013, "dur": 3.158, + "args": { + "External id": 4728572,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059217.653, "dur": 1.809, + "args": { + "External id": 4728573,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059218.574, "dur": 0.793, + "args": { + "External id": 4728574,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059223.767, "dur": 3.882, + "args": { + "External id": 4728575,"Record function id": 0, "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059224.962, "dur": 2.285, + "args": { + "External id": 4728576,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059225.680, "dur": 0.984, + "args": { + "External id": 4728577,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059225.990, "dur": 0.577, + "args": { + "External id": 4728578,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059230.953, "dur": 3.868, + "args": { + "External id": 4728579,"Record function id": 0, "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059232.232, "dur": 2.183, + "args": { + "External id": 4728580,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059233.073, "dur": 0.971, + "args": { + "External id": 4728581,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059233.329, "dur": 0.646, + "args": { + "External id": 4728582,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059238.061, "dur": 4.051, + "args": { + "External id": 4728583,"Record function id": 0, "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360059239.186, "dur": 2.502, + "args": { + "External id": 4728584,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059240.020, "dur": 1.296, + "args": { + "External id": 4728585,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360059240.606, "dur": 0.621, + "args": { + "External id": 4728586,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360059245.985, "dur": 36638.810, + "args": { + "External id": 4728587,"Record function id": 0, "Sequence number": 47018797, "Fwd thread id": 1, "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360059247.306, "dur": 36629.745, + "args": { + "External id": 4728588,"Sequence number": 47018797, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3339 + } + }, + { + "ph": "f", "id": 195, "pid": 1336753, "tid": 1381210, "ts": 1712360059247.306, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1712360059276.997, "dur": 36.504, + "args": { + "External id": 4728589,"Record function id": 0, "Ev Idx": 3340 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1712360059321.031, "dur": 66.073, + "args": { + "External id": 4728590,"Record function id": 0, "Ev Idx": 3341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1712360059393.000, "dur": 36476.840, + "args": { + "External id": 4728591,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360059481.426, "dur": 10.247, + "args": { + "External id": 4728592,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360059501.001, "dur": 6.452, + "args": { + "External id": 4728593,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360059522.367, "dur": 35557.355, + "args": { + "External id": 4728594,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360059535.738, "dur": 35524.877, + "args": { + "External id": 4728595,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360059602.977, "dur": 13.433, + "args": { + "External id": 4728596,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360059622.840, "dur": 35398.053, + "args": { + "External id": 4728597,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360059625.417, "dur": 35394.631, + "args": { + "External id": 4728598,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360059629.413, "dur": 4.912, + "args": { + "External id": 4728599,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360059636.202, "dur": 35379.897, + "args": { + "External id": 4728600,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360095174.894, "dur": 9.754, + "args": { + "External id": 4728601,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360095178.474, "dur": 5.842, + "args": { + "External id": 4728602,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360095220.606, "dur": 351.807, + "args": { + "External id": 4728603,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360095247.013, "dur": 320.778, + "args": { + "External id": 4728604,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3355, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360095257.345, "dur": 304.451, + "args": { + "External id": 4728605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360095599.409, "dur": 2.187, + "args": { + "External id": 4728606,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3357, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360095657.844, "dur": 6.837, + "args": { + "External id": 4728607,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360095707.947, "dur": 1.401, + "args": { + "External id": 4728608,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360095725.689, "dur": 2.966, + "args": { + "External id": 4728609,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360095741.224, "dur": 0.898, + "args": { + "External id": 4728610,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360095753.647, "dur": 0.974, + "args": { + "External id": 4728611,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360095766.645, "dur": 0.794, + "args": { + "External id": 4728612,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360095779.792, "dur": 2.293, + "args": { + "External id": 4728613,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360095795.098, "dur": 1.783, + "args": { + "External id": 4728614,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360095808.841, "dur": 0.714, + "args": { + "External id": 4728615,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360095899.913, "dur": 2714.317, + "args": { + "External id": 4728616,"Record function id": 0, "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1712360095919.430, "dur": 1034.486, + "args": { + "External id": 4728617,"Record function id": 0, "Ev Idx": 3368 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1712360095936.366, "dur": 384.908, + "args": { + "External id": 4728618,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360096058.493, "dur": 4.844, + "args": { + "External id": 4728619,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360096082.538, "dur": 1.597, + "args": { + "External id": 4728620,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360096086.357, "dur": 3.071, + "args": { + "External id": 4728621,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360096090.980, "dur": 0.949, + "args": { + "External id": 4728622,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360096093.444, "dur": 1.250, + "args": { + "External id": 4728623,"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": 1336753, "tid": 1381210, + "ts": 1712360096096.331, "dur": 0.859, + "args": { + "External id": 4728624,"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": 1336753, "tid": 1381210, + "ts": 1712360096098.863, "dur": 2.120, + "args": { + "External id": 4728625,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360096102.354, "dur": 1.483, + "args": { + "External id": 4728626,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360096105.562, "dur": 0.796, + "args": { + "External id": 4728627,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360096107.745, "dur": 0.838, + "args": { + "External id": 4728628,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360096127.728, "dur": 159.686, + "args": { + "External id": 4728629,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360096144.463, "dur": 138.685, + "args": { + "External id": 4728630,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360096168.787, "dur": 14.633, + "args": { + "External id": 4728631,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360096186.606, "dur": 68.347, + "args": { + "External id": 4728632,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360096189.329, "dur": 65.245, + "args": { + "External id": 4728633,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096193.867, "dur": 5.616, + "args": { + "External id": 4728634,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360096201.529, "dur": 52.482, + "args": { + "External id": 4728635,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3386 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.14", "pid": 1336753, "tid": 1381210, + "ts": 1712360096422.282, "dur": 522.674, + "args": { + "External id": 4728636,"Record function id": 0, "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1712360096440.347, "dur": 492.476, + "args": { + "External id": 4728637,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360096505.230, "dur": 4.557, + "args": { + "External id": 4728638,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360096525.131, "dur": 32.298, + "args": { + "External id": 4728639,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096533.401, "dur": 1.493, + "args": { + "External id": 4728640,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096537.215, "dur": 0.501, + "args": { + "External id": 4728641,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096539.419, "dur": 0.364, + "args": { + "External id": 4728642,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096541.818, "dur": 0.342, + "args": { + "External id": 4728643,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096543.967, "dur": 0.388, + "args": { + "External id": 4728644,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096546.063, "dur": 1.862, + "args": { + "External id": 4728645,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096549.756, "dur": 0.419, + "args": { + "External id": 4728646,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096551.882, "dur": 0.357, + "args": { + "External id": 4728647,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096553.580, "dur": 0.351, + "args": { + "External id": 4728648,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360096567.660, "dur": 30.211, + "args": { + "External id": 4728649,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360096628.387, "dur": 93.197, + "args": { + "External id": 4728650,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360096637.615, "dur": 2.956, + "args": { + "External id": 4728651,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360096645.716, "dur": 9.854, + "args": { + "External id": 4728652,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360096649.972, "dur": 5.192, + "args": { + "External id": 4728653,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096653.578, "dur": 0.520, + "args": { + "External id": 4728654,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360096662.804, "dur": 24.454, + "args": { + "External id": 4728655,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096665.217, "dur": 0.419, + "args": { + "External id": 4728656,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096667.384, "dur": 0.305, + "args": { + "External id": 4728657,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096669.121, "dur": 2.141, + "args": { + "External id": 4728658,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096672.885, "dur": 0.328, + "args": { + "External id": 4728659,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096675.480, "dur": 0.382, + "args": { + "External id": 4728660,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096677.385, "dur": 0.516, + "args": { + "External id": 4728661,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096679.672, "dur": 0.521, + "args": { + "External id": 4728662,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096681.802, "dur": 0.322, + "args": { + "External id": 4728663,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360096683.633, "dur": 0.337, + "args": { + "External id": 4728664,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360096697.527, "dur": 17.497, + "args": { + "External id": 4728665,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360096763.518, "dur": 111.189, + "args": { + "External id": 4728666,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360096784.902, "dur": 82.726, + "args": { + "External id": 4728667,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3418, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360096793.770, "dur": 69.261, + "args": { + "External id": 4728668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360096887.467, "dur": 1.841, + "args": { + "External id": 4728669,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3420, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360096961.454, "dur": 1632.160, + "args": { + "External id": 4728670,"Sequence number": 47018796, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3421 + } + }, + { + "ph": "f", "id": 196, "pid": 1336753, "tid": 1381210, "ts": 1712360096961.454, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360097130.872, "dur": 103.232, + "args": { + "External id": 4728671,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360097273.346, "dur": 39.446, + "args": { + "External id": 4728672,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360097330.424, "dur": 48.182, + "args": { + "External id": 4728673,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360097389.141, "dur": 32.003, + "args": { + "External id": 4728674,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360097428.370, "dur": 46.034, + "args": { + "External id": 4728675,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360097481.519, "dur": 27.795, + "args": { + "External id": 4728676,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360097517.027, "dur": 42.472, + "args": { + "External id": 4728677,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360097581.659, "dur": 21.940, + "args": { + "External id": 4728678,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360097621.178, "dur": 27.111, + "args": { + "External id": 4728679,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360097666.442, "dur": 18.770, + "args": { + "External id": 4728680,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360097698.239, "dur": 14.750, + "args": { + "External id": 4728681,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360097721.250, "dur": 25.840, + "args": { + "External id": 4728682,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360097750.377, "dur": 31.574, + "args": { + "External id": 4728683,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360097824.055, "dur": 208.018, + "args": { + "External id": 4728684,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360097899.927, "dur": 5.464, + "args": { + "External id": 4728685,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360097907.281, "dur": 2.136, + "args": { + "External id": 4728686,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360098090.925, "dur": 30.761, + "args": { + "External id": 4728687,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360098133.793, "dur": 14.099, + "args": { + "External id": 4728688,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360098158.415, "dur": 44.950, + "args": { + "External id": 4728689,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360098210.161, "dur": 38.276, + "args": { + "External id": 4728690,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360098256.684, "dur": 20.169, + "args": { + "External id": 4728691,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360098283.085, "dur": 29.227, + "args": { + "External id": 4728692,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360098318.210, "dur": 19.426, + "args": { + "External id": 4728693,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360098345.452, "dur": 29.230, + "args": { + "External id": 4728694,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360098392.281, "dur": 32.774, + "args": { + "External id": 4728695,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360098448.370, "dur": 26.323, + "args": { + "External id": 4728696,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360098489.757, "dur": 17.321, + "args": { + "External id": 4728697,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360098521.582, "dur": 14.333, + "args": { + "External id": 4728698,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360098547.996, "dur": 15.482, + "args": { + "External id": 4728699,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098636.897, "dur": 19.143, + "args": { + "External id": 4728700,"Record function id": 0, "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098640.465, "dur": 14.611, + "args": { + "External id": 4728701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098644.588, "dur": 9.535, + "args": { + "External id": 4728702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098646.631, "dur": 7.369, + "args": { + "External id": 4728703,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098659.928, "dur": 7.283, + "args": { + "External id": 4728704,"Record function id": 0, "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098661.196, "dur": 5.519, + "args": { + "External id": 4728705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098662.171, "dur": 3.965, + "args": { + "External id": 4728706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098663.122, "dur": 2.902, + "args": { + "External id": 4728707,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098670.495, "dur": 4.288, + "args": { + "External id": 4728708,"Record function id": 0, "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098671.858, "dur": 2.519, + "args": { + "External id": 4728709,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098672.351, "dur": 1.605, + "args": { + "External id": 4728710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098672.809, "dur": 1.087, + "args": { + "External id": 4728711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098678.071, "dur": 4.504, + "args": { + "External id": 4728712,"Record function id": 0, "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098679.408, "dur": 2.754, + "args": { + "External id": 4728713,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098680.418, "dur": 1.277, + "args": { + "External id": 4728714,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098680.951, "dur": 0.678, + "args": { + "External id": 4728715,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098685.786, "dur": 4.076, + "args": { + "External id": 4728716,"Record function id": 0, "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098687.043, "dur": 2.404, + "args": { + "External id": 4728717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098687.929, "dur": 1.100, + "args": { + "External id": 4728718,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098688.306, "dur": 0.661, + "args": { + "External id": 4728719,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098693.085, "dur": 4.132, + "args": { + "External id": 4728720,"Record function id": 0, "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098694.255, "dur": 2.537, + "args": { + "External id": 4728721,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098695.140, "dur": 1.061, + "args": { + "External id": 4728722,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098695.555, "dur": 0.550, + "args": { + "External id": 4728723,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098700.419, "dur": 3.894, + "args": { + "External id": 4728724,"Record function id": 0, "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098701.508, "dur": 2.387, + "args": { + "External id": 4728725,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098702.170, "dur": 1.313, + "args": { + "External id": 4728726,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098702.820, "dur": 0.568, + "args": { + "External id": 4728727,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098707.408, "dur": 3.905, + "args": { + "External id": 4728728,"Record function id": 0, "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098708.732, "dur": 2.178, + "args": { + "External id": 4728729,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098709.320, "dur": 1.157, + "args": { + "External id": 4728730,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098709.586, "dur": 0.825, + "args": { + "External id": 4728731,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098714.428, "dur": 5.230, + "args": { + "External id": 4728732,"Record function id": 0, "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360098715.425, "dur": 3.820, + "args": { + "External id": 4728733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098715.945, "dur": 2.912, + "args": { + "External id": 4728734,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360098716.468, "dur": 2.278, + "args": { + "External id": 4728735,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360098727.284, "dur": 36526.509, + "args": { + "External id": 4728736,"Record function id": 0, "Sequence number": 47018795, "Fwd thread id": 1, "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360098728.774, "dur": 36516.254, + "args": { + "External id": 4728737,"Sequence number": 47018795, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3488 + } + }, + { + "ph": "f", "id": 197, "pid": 1336753, "tid": 1381210, "ts": 1712360098728.774, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1712360098755.519, "dur": 40.490, + "args": { + "External id": 4728738,"Record function id": 0, "Ev Idx": 3489 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1712360098803.459, "dur": 62.095, + "args": { + "External id": 4728739,"Record function id": 0, "Ev Idx": 3490 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1712360098871.126, "dur": 36365.886, + "args": { + "External id": 4728740,"Record function id": 0, "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360098955.511, "dur": 6.801, + "args": { + "External id": 4728741,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360098971.684, "dur": 4.604, + "args": { + "External id": 4728742,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360099032.740, "dur": 35357.390, + "args": { + "External id": 4728743,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360099046.676, "dur": 35334.746, + "args": { + "External id": 4728744,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360099122.106, "dur": 18.284, + "args": { + "External id": 4728745,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360099146.993, "dur": 35197.909, + "args": { + "External id": 4728746,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360099149.773, "dur": 35194.374, + "args": { + "External id": 4728747,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360099153.810, "dur": 6.576, + "args": { + "External id": 4728748,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360099162.749, "dur": 35177.893, + "args": { + "External id": 4728749,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360134477.527, "dur": 9.089, + "args": { + "External id": 4728750,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360134480.908, "dur": 5.358, + "args": { + "External id": 4728751,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360134518.305, "dur": 371.376, + "args": { + "External id": 4728752,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360134544.378, "dur": 340.469, + "args": { + "External id": 4728753,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3504, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360134554.968, "dur": 323.898, + "args": { + "External id": 4728754,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360134909.021, "dur": 2.577, + "args": { + "External id": 4728755,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3506, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360134968.917, "dur": 6.379, + "args": { + "External id": 4728756,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135053.818, "dur": 4.460, + "args": { + "External id": 4728757,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135093.662, "dur": 1.516, + "args": { + "External id": 4728758,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135108.636, "dur": 1.053, + "args": { + "External id": 4728759,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135121.469, "dur": 0.780, + "args": { + "External id": 4728760,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135133.988, "dur": 2.700, + "args": { + "External id": 4728761,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135149.014, "dur": 0.957, + "args": { + "External id": 4728762,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135160.752, "dur": 2.423, + "args": { + "External id": 4728763,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135173.948, "dur": 0.755, + "args": { + "External id": 4728764,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360135270.253, "dur": 2814.225, + "args": { + "External id": 4728765,"Record function id": 0, "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1712360135290.144, "dur": 1006.184, + "args": { + "External id": 4728766,"Record function id": 0, "Ev Idx": 3517 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1712360135305.290, "dur": 308.511, + "args": { + "External id": 4728767,"Record function id": 0, "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135383.036, "dur": 5.755, + "args": { + "External id": 4728768,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135391.630, "dur": 1.182, + "args": { + "External id": 4728769,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135394.598, "dur": 1.034, + "args": { + "External id": 4728770,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135397.506, "dur": 1.168, + "args": { + "External id": 4728771,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135400.090, "dur": 1.142, + "args": { + "External id": 4728772,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135402.946, "dur": 0.763, + "args": { + "External id": 4728773,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135405.347, "dur": 1.824, + "args": { + "External id": 4728774,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135408.577, "dur": 1.119, + "args": { + "External id": 4728775,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135410.968, "dur": 3.111, + "args": { + "External id": 4728776,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360135415.957, "dur": 0.981, + "args": { + "External id": 4728777,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360135433.820, "dur": 149.801, + "args": { + "External id": 4728778,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360135449.345, "dur": 130.549, + "args": { + "External id": 4728779,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360135473.006, "dur": 11.900, + "args": { + "External id": 4728780,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360135487.813, "dur": 65.148, + "args": { + "External id": 4728781,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360135490.410, "dur": 62.226, + "args": { + "External id": 4728782,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135494.357, "dur": 4.857, + "args": { + "External id": 4728783,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360135500.966, "dur": 50.895, + "args": { + "External id": 4728784,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3535 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.13", "pid": 1336753, "tid": 1381210, + "ts": 1712360135701.521, "dur": 583.437, + "args": { + "External id": 4728785,"Record function id": 0, "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1712360135716.832, "dur": 554.850, + "args": { + "External id": 4728786,"Record function id": 0, "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360135772.542, "dur": 4.344, + "args": { + "External id": 4728787,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360135792.166, "dur": 26.914, + "args": { + "External id": 4728788,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135796.545, "dur": 0.994, + "args": { + "External id": 4728789,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135799.245, "dur": 0.587, + "args": { + "External id": 4728790,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135801.547, "dur": 0.430, + "args": { + "External id": 4728791,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135803.235, "dur": 2.461, + "args": { + "External id": 4728792,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135807.425, "dur": 0.383, + "args": { + "External id": 4728793,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135809.131, "dur": 0.424, + "args": { + "External id": 4728794,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135811.212, "dur": 0.351, + "args": { + "External id": 4728795,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135813.040, "dur": 0.365, + "args": { + "External id": 4728796,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135814.966, "dur": 0.434, + "args": { + "External id": 4728797,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360135828.723, "dur": 28.382, + "args": { + "External id": 4728798,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360135886.459, "dur": 145.048, + "args": { + "External id": 4728799,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360135896.531, "dur": 2.621, + "args": { + "External id": 4728800,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360135908.643, "dur": 9.797, + "args": { + "External id": 4728801,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360135912.751, "dur": 5.290, + "args": { + "External id": 4728802,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135916.338, "dur": 0.658, + "args": { + "External id": 4728803,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360135927.599, "dur": 25.684, + "args": { + "External id": 4728804,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135929.673, "dur": 2.619, + "args": { + "External id": 4728805,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135933.922, "dur": 0.423, + "args": { + "External id": 4728806,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135936.108, "dur": 0.366, + "args": { + "External id": 4728807,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135938.214, "dur": 0.487, + "args": { + "External id": 4728808,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135940.495, "dur": 0.419, + "args": { + "External id": 4728809,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135942.308, "dur": 0.338, + "args": { + "External id": 4728810,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135944.269, "dur": 0.366, + "args": { + "External id": 4728811,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135945.914, "dur": 0.338, + "args": { + "External id": 4728812,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360135947.774, "dur": 2.167, + "args": { + "External id": 4728813,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360135964.490, "dur": 57.569, + "args": { + "External id": 4728814,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360136091.944, "dur": 112.015, + "args": { + "External id": 4728815,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360136114.264, "dur": 85.751, + "args": { + "External id": 4728816,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3567, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360136124.481, "dur": 71.454, + "args": { + "External id": 4728817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360136216.966, "dur": 1.923, + "args": { + "External id": 4728818,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3569, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360136303.758, "dur": 1744.301, + "args": { + "External id": 4728819,"Sequence number": 47018794, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3570 + } + }, + { + "ph": "f", "id": 198, "pid": 1336753, "tid": 1381210, "ts": 1712360136303.758, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360136417.280, "dur": 98.819, + "args": { + "External id": 4728820,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360136551.318, "dur": 41.384, + "args": { + "External id": 4728821,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360136612.388, "dur": 50.444, + "args": { + "External id": 4728822,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360136672.050, "dur": 32.187, + "args": { + "External id": 4728823,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360136711.013, "dur": 46.634, + "args": { + "External id": 4728824,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360136764.859, "dur": 28.852, + "args": { + "External id": 4728825,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360136803.232, "dur": 42.094, + "args": { + "External id": 4728826,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360136866.309, "dur": 20.944, + "args": { + "External id": 4728827,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360136903.474, "dur": 27.473, + "args": { + "External id": 4728828,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360136949.786, "dur": 17.476, + "args": { + "External id": 4728829,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360136979.198, "dur": 59.812, + "args": { + "External id": 4728830,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360137051.473, "dur": 49.333, + "args": { + "External id": 4728831,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360137105.939, "dur": 34.774, + "args": { + "External id": 4728832,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360137244.469, "dur": 173.973, + "args": { + "External id": 4728833,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360137325.071, "dur": 5.748, + "args": { + "External id": 4728834,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360137333.016, "dur": 1.861, + "args": { + "External id": 4728835,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360137454.348, "dur": 24.287, + "args": { + "External id": 4728836,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360137490.458, "dur": 14.412, + "args": { + "External id": 4728837,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360137516.121, "dur": 40.662, + "args": { + "External id": 4728838,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360137564.880, "dur": 38.038, + "args": { + "External id": 4728839,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360137609.523, "dur": 19.297, + "args": { + "External id": 4728840,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360137634.953, "dur": 29.967, + "args": { + "External id": 4728841,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360137671.456, "dur": 38.033, + "args": { + "External id": 4728842,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360137724.265, "dur": 31.746, + "args": { + "External id": 4728843,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360137774.986, "dur": 21.217, + "args": { + "External id": 4728844,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360137848.094, "dur": 25.007, + "args": { + "External id": 4728845,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360137889.242, "dur": 16.411, + "args": { + "External id": 4728846,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360137921.152, "dur": 16.364, + "args": { + "External id": 4728847,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360137948.642, "dur": 16.259, + "args": { + "External id": 4728848,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138112.144, "dur": 17.716, + "args": { + "External id": 4728849,"Record function id": 0, "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138115.747, "dur": 13.154, + "args": { + "External id": 4728850,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138119.678, "dur": 7.955, + "args": { + "External id": 4728851,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138121.362, "dur": 6.149, + "args": { + "External id": 4728852,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138133.689, "dur": 4.997, + "args": { + "External id": 4728853,"Record function id": 0, "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138135.073, "dur": 3.146, + "args": { + "External id": 4728854,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138135.930, "dur": 1.746, + "args": { + "External id": 4728855,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138136.539, "dur": 1.036, + "args": { + "External id": 4728856,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138141.990, "dur": 4.290, + "args": { + "External id": 4728857,"Record function id": 0, "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138143.288, "dur": 2.564, + "args": { + "External id": 4728858,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138143.891, "dur": 1.394, + "args": { + "External id": 4728859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138144.308, "dur": 0.896, + "args": { + "External id": 4728860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138149.445, "dur": 4.131, + "args": { + "External id": 4728861,"Record function id": 0, "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138150.895, "dur": 2.263, + "args": { + "External id": 4728862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138151.365, "dur": 1.353, + "args": { + "External id": 4728863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138151.881, "dur": 0.759, + "args": { + "External id": 4728864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138156.658, "dur": 3.247, + "args": { + "External id": 4728865,"Record function id": 0, "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138157.665, "dur": 1.841, + "args": { + "External id": 4728866,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138158.140, "dur": 0.891, + "args": { + "External id": 4728867,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138158.411, "dur": 0.555, + "args": { + "External id": 4728868,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138163.064, "dur": 3.898, + "args": { + "External id": 4728869,"Record function id": 0, "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138164.511, "dur": 2.053, + "args": { + "External id": 4728870,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138164.984, "dur": 1.156, + "args": { + "External id": 4728871,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138165.411, "dur": 0.630, + "args": { + "External id": 4728872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138170.284, "dur": 3.600, + "args": { + "External id": 4728873,"Record function id": 0, "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138171.431, "dur": 2.058, + "args": { + "External id": 4728874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138172.046, "dur": 1.015, + "args": { + "External id": 4728875,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138172.343, "dur": 0.616, + "args": { + "External id": 4728876,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138177.146, "dur": 5.368, + "args": { + "External id": 4728877,"Record function id": 0, "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138178.122, "dur": 3.964, + "args": { + "External id": 4728878,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138178.752, "dur": 2.925, + "args": { + "External id": 4728879,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138179.063, "dur": 2.530, + "args": { + "External id": 4728880,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138185.697, "dur": 4.559, + "args": { + "External id": 4728881,"Record function id": 0, "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360138186.736, "dur": 3.122, + "args": { + "External id": 4728882,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138187.583, "dur": 1.608, + "args": { + "External id": 4728883,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360138188.033, "dur": 1.069, + "args": { + "External id": 4728884,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360138194.256, "dur": 35985.998, + "args": { + "External id": 4728885,"Record function id": 0, "Sequence number": 47018793, "Fwd thread id": 1, "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360138195.698, "dur": 35976.571, + "args": { + "External id": 4728886,"Sequence number": 47018793, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3637 + } + }, + { + "ph": "f", "id": 199, "pid": 1336753, "tid": 1381210, "ts": 1712360138195.698, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1712360138230.221, "dur": 37.728, + "args": { + "External id": 4728887,"Record function id": 0, "Ev Idx": 3638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1712360138279.072, "dur": 67.699, + "args": { + "External id": 4728888,"Record function id": 0, "Ev Idx": 3639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1712360138352.210, "dur": 35811.889, + "args": { + "External id": 4728889,"Record function id": 0, "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360138448.381, "dur": 6.729, + "args": { + "External id": 4728890,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360138464.288, "dur": 4.880, + "args": { + "External id": 4728891,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360138483.934, "dur": 34758.114, + "args": { + "External id": 4728892,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360138497.030, "dur": 34735.324, + "args": { + "External id": 4728893,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360138566.238, "dur": 16.477, + "args": { + "External id": 4728894,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360138589.033, "dur": 34603.820, + "args": { + "External id": 4728895,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360138591.692, "dur": 34600.377, + "args": { + "External id": 4728896,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360138595.616, "dur": 5.231, + "args": { + "External id": 4728897,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360138602.688, "dur": 34585.819, + "args": { + "External id": 4728898,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360173331.779, "dur": 8.987, + "args": { + "External id": 4728899,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360173335.114, "dur": 5.351, + "args": { + "External id": 4728900,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360173370.314, "dur": 414.690, + "args": { + "External id": 4728901,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360173396.045, "dur": 383.917, + "args": { + "External id": 4728902,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3653, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360173406.551, "dur": 367.625, + "args": { + "External id": 4728903,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360173805.335, "dur": 2.255, + "args": { + "External id": 4728904,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3655, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360173867.500, "dur": 6.820, + "args": { + "External id": 4728905,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360173924.987, "dur": 1.297, + "args": { + "External id": 4728906,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360173942.861, "dur": 4.188, + "args": { + "External id": 4728907,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360173958.834, "dur": 0.903, + "args": { + "External id": 4728908,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360173971.570, "dur": 0.941, + "args": { + "External id": 4728909,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174036.270, "dur": 1.496, + "args": { + "External id": 4728910,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174052.077, "dur": 1.235, + "args": { + "External id": 4728911,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174078.664, "dur": 2.499, + "args": { + "External id": 4728912,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174096.029, "dur": 0.799, + "args": { + "External id": 4728913,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360174197.644, "dur": 2672.100, + "args": { + "External id": 4728914,"Record function id": 0, "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1712360174218.804, "dur": 1027.820, + "args": { + "External id": 4728915,"Record function id": 0, "Ev Idx": 3666 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1712360174234.539, "dur": 336.681, + "args": { + "External id": 4728916,"Record function id": 0, "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174314.717, "dur": 3.874, + "args": { + "External id": 4728917,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174321.646, "dur": 1.118, + "args": { + "External id": 4728918,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174324.431, "dur": 1.020, + "args": { + "External id": 4728919,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174327.164, "dur": 0.914, + "args": { + "External id": 4728920,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174329.505, "dur": 1.027, + "args": { + "External id": 4728921,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174332.253, "dur": 0.742, + "args": { + "External id": 4728922,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174334.632, "dur": 1.817, + "args": { + "External id": 4728923,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174337.759, "dur": 2.936, + "args": { + "External id": 4728924,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174342.049, "dur": 0.954, + "args": { + "External id": 4728925,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360174344.503, "dur": 0.806, + "args": { + "External id": 4728926,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360174365.725, "dur": 172.805, + "args": { + "External id": 4728927,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360174382.388, "dur": 151.326, + "args": { + "External id": 4728928,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360174421.152, "dur": 12.962, + "args": { + "External id": 4728929,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360174437.211, "dur": 68.507, + "args": { + "External id": 4728930,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360174439.992, "dur": 65.348, + "args": { + "External id": 4728931,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174444.114, "dur": 5.763, + "args": { + "External id": 4728932,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360174451.731, "dur": 53.039, + "args": { + "External id": 4728933,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3684 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.12", "pid": 1336753, "tid": 1381210, + "ts": 1712360174660.893, "dur": 578.093, + "args": { + "External id": 4728934,"Record function id": 0, "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1712360174677.433, "dur": 549.183, + "args": { + "External id": 4728935,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360174736.745, "dur": 4.652, + "args": { + "External id": 4728936,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360174756.547, "dur": 27.950, + "args": { + "External id": 4728937,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174761.521, "dur": 1.060, + "args": { + "External id": 4728938,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174764.487, "dur": 0.448, + "args": { + "External id": 4728939,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174766.484, "dur": 2.242, + "args": { + "External id": 4728940,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174770.721, "dur": 0.475, + "args": { + "External id": 4728941,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174772.541, "dur": 0.395, + "args": { + "External id": 4728942,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174774.380, "dur": 0.522, + "args": { + "External id": 4728943,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174776.364, "dur": 0.460, + "args": { + "External id": 4728944,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174778.309, "dur": 0.319, + "args": { + "External id": 4728945,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174780.376, "dur": 0.357, + "args": { + "External id": 4728946,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360174795.113, "dur": 28.087, + "args": { + "External id": 4728947,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360174852.996, "dur": 92.786, + "args": { + "External id": 4728948,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360174862.477, "dur": 3.178, + "args": { + "External id": 4728949,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360174870.977, "dur": 11.567, + "args": { + "External id": 4728950,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360174875.163, "dur": 6.977, + "args": { + "External id": 4728951,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174878.956, "dur": 2.147, + "args": { + "External id": 4728952,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360174888.995, "dur": 22.393, + "args": { + "External id": 4728953,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174891.285, "dur": 0.392, + "args": { + "External id": 4728954,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174893.366, "dur": 0.492, + "args": { + "External id": 4728955,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174895.506, "dur": 0.430, + "args": { + "External id": 4728956,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174897.298, "dur": 0.360, + "args": { + "External id": 4728957,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174899.071, "dur": 0.767, + "args": { + "External id": 4728958,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174901.501, "dur": 0.472, + "args": { + "External id": 4728959,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174903.289, "dur": 0.500, + "args": { + "External id": 4728960,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174905.399, "dur": 1.603, + "args": { + "External id": 4728961,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360174908.244, "dur": 0.383, + "args": { + "External id": 4728962,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360174921.065, "dur": 17.737, + "args": { + "External id": 4728963,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360175030.566, "dur": 128.741, + "args": { + "External id": 4728964,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360175053.892, "dur": 101.902, + "args": { + "External id": 4728965,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3716, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360175063.733, "dur": 87.400, + "args": { + "External id": 4728966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360175173.318, "dur": 2.036, + "args": { + "External id": 4728967,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3718, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360175254.585, "dur": 1592.393, + "args": { + "External id": 4728968,"Sequence number": 47018792, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3719 + } + }, + { + "ph": "f", "id": 200, "pid": 1336753, "tid": 1381210, "ts": 1712360175254.585, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360175362.707, "dur": 98.983, + "args": { + "External id": 4728969,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360175499.746, "dur": 39.890, + "args": { + "External id": 4728970,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360175557.551, "dur": 49.065, + "args": { + "External id": 4728971,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360175615.727, "dur": 32.758, + "args": { + "External id": 4728972,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360175655.886, "dur": 46.874, + "args": { + "External id": 4728973,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360175710.203, "dur": 27.367, + "args": { + "External id": 4728974,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360175746.819, "dur": 44.133, + "args": { + "External id": 4728975,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360175812.716, "dur": 21.696, + "args": { + "External id": 4728976,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360175851.303, "dur": 29.069, + "args": { + "External id": 4728977,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360175899.748, "dur": 18.990, + "args": { + "External id": 4728978,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360175933.858, "dur": 14.593, + "args": { + "External id": 4728979,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360175957.940, "dur": 76.417, + "args": { + "External id": 4728980,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360176039.697, "dur": 55.446, + "args": { + "External id": 4728981,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360176124.719, "dur": 170.299, + "args": { + "External id": 4728982,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360176203.797, "dur": 5.755, + "args": { + "External id": 4728983,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360176211.580, "dur": 2.277, + "args": { + "External id": 4728984,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360176330.478, "dur": 25.261, + "args": { + "External id": 4728985,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360176381.120, "dur": 15.077, + "args": { + "External id": 4728986,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360176406.414, "dur": 38.619, + "args": { + "External id": 4728987,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360176452.366, "dur": 34.680, + "args": { + "External id": 4728988,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360176494.329, "dur": 19.873, + "args": { + "External id": 4728989,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360176520.002, "dur": 30.036, + "args": { + "External id": 4728990,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360176557.562, "dur": 19.817, + "args": { + "External id": 4728991,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360176585.196, "dur": 43.910, + "args": { + "External id": 4728992,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360176653.777, "dur": 27.597, + "args": { + "External id": 4728993,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360176697.721, "dur": 24.936, + "args": { + "External id": 4728994,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360176739.882, "dur": 16.221, + "args": { + "External id": 4728995,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360176773.445, "dur": 13.870, + "args": { + "External id": 4728996,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360176803.047, "dur": 15.519, + "args": { + "External id": 4728997,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176892.354, "dur": 14.816, + "args": { + "External id": 4728998,"Record function id": 0, "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176895.918, "dur": 10.307, + "args": { + "External id": 4728999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176899.667, "dur": 5.666, + "args": { + "External id": 4729000,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176901.394, "dur": 3.813, + "args": { + "External id": 4729001,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176911.054, "dur": 4.775, + "args": { + "External id": 4729002,"Record function id": 0, "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176912.322, "dur": 3.069, + "args": { + "External id": 4729003,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176912.953, "dur": 1.862, + "args": { + "External id": 4729004,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176913.711, "dur": 0.973, + "args": { + "External id": 4729005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176919.066, "dur": 4.329, + "args": { + "External id": 4729006,"Record function id": 0, "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176920.243, "dur": 2.735, + "args": { + "External id": 4729007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176920.760, "dur": 1.645, + "args": { + "External id": 4729008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176921.495, "dur": 0.834, + "args": { + "External id": 4729009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176926.660, "dur": 4.026, + "args": { + "External id": 4729010,"Record function id": 0, "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176927.704, "dur": 2.577, + "args": { + "External id": 4729011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176928.701, "dur": 1.195, + "args": { + "External id": 4729012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176928.974, "dur": 0.857, + "args": { + "External id": 4729013,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176933.760, "dur": 3.705, + "args": { + "External id": 4729014,"Record function id": 0, "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176934.936, "dur": 2.122, + "args": { + "External id": 4729015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176935.491, "dur": 1.143, + "args": { + "External id": 4729016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176935.745, "dur": 0.824, + "args": { + "External id": 4729017,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176940.625, "dur": 3.680, + "args": { + "External id": 4729018,"Record function id": 0, "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176941.707, "dur": 2.212, + "args": { + "External id": 4729019,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176942.349, "dur": 1.125, + "args": { + "External id": 4729020,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176942.792, "dur": 0.552, + "args": { + "External id": 4729021,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176947.514, "dur": 5.521, + "args": { + "External id": 4729022,"Record function id": 0, "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176948.545, "dur": 4.087, + "args": { + "External id": 4729023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176949.024, "dur": 3.070, + "args": { + "External id": 4729024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176949.331, "dur": 2.687, + "args": { + "External id": 4729025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176956.253, "dur": 4.020, + "args": { + "External id": 4729026,"Record function id": 0, "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176957.447, "dur": 2.424, + "args": { + "External id": 4729027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176958.080, "dur": 1.386, + "args": { + "External id": 4729028,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176958.420, "dur": 0.949, + "args": { + "External id": 4729029,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176963.373, "dur": 3.724, + "args": { + "External id": 4729030,"Record function id": 0, "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360176964.309, "dur": 2.388, + "args": { + "External id": 4729031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176964.809, "dur": 1.432, + "args": { + "External id": 4729032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360176965.396, "dur": 0.758, + "args": { + "External id": 4729033,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360176970.812, "dur": 36357.952, + "args": { + "External id": 4729034,"Record function id": 0, "Sequence number": 47018791, "Fwd thread id": 1, "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360176972.290, "dur": 36348.404, + "args": { + "External id": 4729035,"Sequence number": 47018791, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3786 + } + }, + { + "ph": "f", "id": 201, "pid": 1336753, "tid": 1381210, "ts": 1712360176972.290, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1712360177039.440, "dur": 54.037, + "args": { + "External id": 4729036,"Record function id": 0, "Ev Idx": 3787 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1712360177102.333, "dur": 64.267, + "args": { + "External id": 4729037,"Record function id": 0, "Ev Idx": 3788 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1712360177172.605, "dur": 36140.667, + "args": { + "External id": 4729038,"Record function id": 0, "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360177268.501, "dur": 6.939, + "args": { + "External id": 4729039,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360177286.121, "dur": 5.136, + "args": { + "External id": 4729040,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360177306.156, "dur": 35167.214, + "args": { + "External id": 4729041,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360177319.347, "dur": 35144.677, + "args": { + "External id": 4729042,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360177380.805, "dur": 13.643, + "args": { + "External id": 4729043,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360177400.711, "dur": 35023.815, + "args": { + "External id": 4729044,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360177403.364, "dur": 35020.347, + "args": { + "External id": 4729045,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360177407.462, "dur": 5.053, + "args": { + "External id": 4729046,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360177414.616, "dur": 35004.988, + "args": { + "External id": 4729047,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360212564.347, "dur": 9.300, + "args": { + "External id": 4729048,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360212567.820, "dur": 5.453, + "args": { + "External id": 4729049,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360212603.494, "dur": 355.911, + "args": { + "External id": 4729050,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360212630.025, "dur": 324.926, + "args": { + "External id": 4729051,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3802, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360212640.611, "dur": 308.230, + "args": { + "External id": 4729052,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360212976.278, "dur": 2.027, + "args": { + "External id": 4729053,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3804, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213098.292, "dur": 9.022, + "args": { + "External id": 4729054,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213152.704, "dur": 1.455, + "args": { + "External id": 4729055,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213171.343, "dur": 1.082, + "args": { + "External id": 4729056,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213185.679, "dur": 0.826, + "args": { + "External id": 4729057,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213197.455, "dur": 2.549, + "args": { + "External id": 4729058,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213210.636, "dur": 1.073, + "args": { + "External id": 4729059,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213223.339, "dur": 0.855, + "args": { + "External id": 4729060,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213236.252, "dur": 1.813, + "args": { + "External id": 4729061,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213248.382, "dur": 2.168, + "args": { + "External id": 4729062,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360213344.927, "dur": 2607.532, + "args": { + "External id": 4729063,"Record function id": 0, "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1712360213368.119, "dur": 1007.658, + "args": { + "External id": 4729064,"Record function id": 0, "Ev Idx": 3815 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1712360213383.871, "dur": 311.680, + "args": { + "External id": 4729065,"Record function id": 0, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213463.634, "dur": 4.255, + "args": { + "External id": 4729066,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213471.055, "dur": 1.177, + "args": { + "External id": 4729067,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213474.002, "dur": 1.023, + "args": { + "External id": 4729068,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213476.553, "dur": 1.049, + "args": { + "External id": 4729069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213479.082, "dur": 1.015, + "args": { + "External id": 4729070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213481.908, "dur": 1.035, + "args": { + "External id": 4729071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213484.596, "dur": 3.214, + "args": { + "External id": 4729072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213489.183, "dur": 1.065, + "args": { + "External id": 4729073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213491.914, "dur": 0.685, + "args": { + "External id": 4729074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360213494.248, "dur": 0.892, + "args": { + "External id": 4729075,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360213512.393, "dur": 153.210, + "args": { + "External id": 4729076,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360213528.625, "dur": 132.656, + "args": { + "External id": 4729077,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360213550.325, "dur": 13.438, + "args": { + "External id": 4729078,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360213566.717, "dur": 67.115, + "args": { + "External id": 4729079,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360213569.335, "dur": 64.117, + "args": { + "External id": 4729080,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213573.585, "dur": 5.056, + "args": { + "External id": 4729081,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360213580.517, "dur": 52.298, + "args": { + "External id": 4729082,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3833 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.11", "pid": 1336753, "tid": 1381210, + "ts": 1712360213784.173, "dur": 584.210, + "args": { + "External id": 4729083,"Record function id": 0, "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1712360213800.262, "dur": 555.938, + "args": { + "External id": 4729084,"Record function id": 0, "Ev Idx": 3835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360213858.565, "dur": 5.469, + "args": { + "External id": 4729085,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360213879.894, "dur": 27.906, + "args": { + "External id": 4729086,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213884.667, "dur": 1.453, + "args": { + "External id": 4729087,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213888.001, "dur": 2.411, + "args": { + "External id": 4729088,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213892.077, "dur": 0.582, + "args": { + "External id": 4729089,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213894.261, "dur": 0.580, + "args": { + "External id": 4729090,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213896.508, "dur": 0.435, + "args": { + "External id": 4729091,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213898.488, "dur": 0.358, + "args": { + "External id": 4729092,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213900.765, "dur": 0.391, + "args": { + "External id": 4729093,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213902.742, "dur": 0.472, + "args": { + "External id": 4729094,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360213904.604, "dur": 0.325, + "args": { + "External id": 4729095,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360213916.943, "dur": 29.067, + "args": { + "External id": 4729096,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360213975.059, "dur": 166.738, + "args": { + "External id": 4729097,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360214027.781, "dur": 6.689, + "args": { + "External id": 4729098,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360214040.518, "dur": 10.874, + "args": { + "External id": 4729099,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360214044.867, "dur": 6.133, + "args": { + "External id": 4729100,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214048.675, "dur": 0.805, + "args": { + "External id": 4729101,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360214058.429, "dur": 40.143, + "args": { + "External id": 4729102,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214060.966, "dur": 0.486, + "args": { + "External id": 4729103,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214063.324, "dur": 0.422, + "args": { + "External id": 4729104,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214079.384, "dur": 0.591, + "args": { + "External id": 4729105,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214082.077, "dur": 0.551, + "args": { + "External id": 4729106,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214084.362, "dur": 0.433, + "args": { + "External id": 4729107,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214086.393, "dur": 0.335, + "args": { + "External id": 4729108,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214088.359, "dur": 2.331, + "args": { + "External id": 4729109,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214092.376, "dur": 0.335, + "args": { + "External id": 4729110,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360214094.184, "dur": 0.382, + "args": { + "External id": 4729111,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360214111.890, "dur": 22.010, + "args": { + "External id": 4729112,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360214189.466, "dur": 104.466, + "args": { + "External id": 4729113,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360214211.447, "dur": 79.126, + "args": { + "External id": 4729114,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3865, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360214221.134, "dur": 65.421, + "args": { + "External id": 4729115,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360214306.335, "dur": 1.888, + "args": { + "External id": 4729116,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3867, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360214382.696, "dur": 1549.850, + "args": { + "External id": 4729117,"Sequence number": 47018790, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3868 + } + }, + { + "ph": "f", "id": 202, "pid": 1336753, "tid": 1381210, "ts": 1712360214382.696, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360214488.364, "dur": 97.213, + "args": { + "External id": 4729118,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360214622.155, "dur": 37.966, + "args": { + "External id": 4729119,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360214677.973, "dur": 46.050, + "args": { + "External id": 4729120,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360214732.809, "dur": 31.337, + "args": { + "External id": 4729121,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360214770.961, "dur": 45.092, + "args": { + "External id": 4729122,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360214825.465, "dur": 27.569, + "args": { + "External id": 4729123,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360214860.213, "dur": 42.181, + "args": { + "External id": 4729124,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360214922.147, "dur": 23.712, + "args": { + "External id": 4729125,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360214962.558, "dur": 77.040, + "args": { + "External id": 4729126,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360215062.626, "dur": 35.253, + "args": { + "External id": 4729127,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360215115.826, "dur": 16.116, + "args": { + "External id": 4729128,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360215143.867, "dur": 36.649, + "args": { + "External id": 4729129,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360215184.026, "dur": 36.753, + "args": { + "External id": 4729130,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360215248.002, "dur": 168.371, + "args": { + "External id": 4729131,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360215323.790, "dur": 6.129, + "args": { + "External id": 4729132,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360215331.970, "dur": 3.633, + "args": { + "External id": 4729133,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360215448.071, "dur": 22.695, + "args": { + "External id": 4729134,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360215481.437, "dur": 13.941, + "args": { + "External id": 4729135,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360215506.722, "dur": 32.064, + "args": { + "External id": 4729136,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360215545.524, "dur": 36.997, + "args": { + "External id": 4729137,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360215589.077, "dur": 20.468, + "args": { + "External id": 4729138,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360215616.830, "dur": 29.332, + "args": { + "External id": 4729139,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360215652.911, "dur": 19.749, + "args": { + "External id": 4729140,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360215679.923, "dur": 29.562, + "args": { + "External id": 4729141,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360215725.796, "dur": 23.282, + "args": { + "External id": 4729142,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360215776.887, "dur": 34.338, + "args": { + "External id": 4729143,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360215829.150, "dur": 16.505, + "args": { + "External id": 4729144,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360215859.990, "dur": 13.117, + "args": { + "External id": 4729145,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360215886.836, "dur": 19.057, + "args": { + "External id": 4729146,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360215978.130, "dur": 55.875, + "args": { + "External id": 4729147,"Record function id": 0, "Ev Idx": 3898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216019.849, "dur": 12.416, + "args": { + "External id": 4729148,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216024.245, "dur": 6.501, + "args": { + "External id": 4729149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216025.995, "dur": 4.441, + "args": { + "External id": 4729150,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216040.198, "dur": 5.656, + "args": { + "External id": 4729151,"Record function id": 0, "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216042.047, "dur": 3.307, + "args": { + "External id": 4729152,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216042.681, "dur": 2.054, + "args": { + "External id": 4729153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216043.555, "dur": 1.083, + "args": { + "External id": 4729154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216049.213, "dur": 5.203, + "args": { + "External id": 4729155,"Record function id": 0, "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216050.925, "dur": 3.077, + "args": { + "External id": 4729156,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216051.716, "dur": 1.831, + "args": { + "External id": 4729157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216052.194, "dur": 1.287, + "args": { + "External id": 4729158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216057.588, "dur": 5.944, + "args": { + "External id": 4729159,"Record function id": 0, "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216059.056, "dur": 4.078, + "args": { + "External id": 4729160,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216059.531, "dur": 3.194, + "args": { + "External id": 4729161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216059.853, "dur": 2.809, + "args": { + "External id": 4729162,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216086.898, "dur": 5.756, + "args": { + "External id": 4729163,"Record function id": 0, "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216088.422, "dur": 3.609, + "args": { + "External id": 4729164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216089.422, "dur": 1.830, + "args": { + "External id": 4729165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216089.813, "dur": 1.260, + "args": { + "External id": 4729166,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216095.882, "dur": 3.861, + "args": { + "External id": 4729167,"Record function id": 0, "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216097.122, "dur": 2.205, + "args": { + "External id": 4729168,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216097.859, "dur": 1.043, + "args": { + "External id": 4729169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216098.351, "dur": 0.445, + "args": { + "External id": 4729170,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216102.992, "dur": 4.244, + "args": { + "External id": 4729171,"Record function id": 0, "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216104.411, "dur": 2.400, + "args": { + "External id": 4729172,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216105.225, "dur": 1.151, + "args": { + "External id": 4729173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216105.569, "dur": 0.723, + "args": { + "External id": 4729174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216110.491, "dur": 4.195, + "args": { + "External id": 4729175,"Record function id": 0, "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216111.638, "dur": 2.646, + "args": { + "External id": 4729176,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216112.344, "dur": 1.500, + "args": { + "External id": 4729177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216113.091, "dur": 0.691, + "args": { + "External id": 4729178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216117.926, "dur": 26.404, + "args": { + "External id": 4729179,"Record function id": 0, "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360216119.218, "dur": 24.678, + "args": { + "External id": 4729180,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216119.782, "dur": 23.558, + "args": { + "External id": 4729181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360216142.550, "dur": 0.637, + "args": { + "External id": 4729182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360216148.584, "dur": 36386.996, + "args": { + "External id": 4729183,"Record function id": 0, "Sequence number": 47018789, "Fwd thread id": 1, "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360216149.973, "dur": 36374.110, + "args": { + "External id": 4729184,"Sequence number": 47018789, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3935 + } + }, + { + "ph": "f", "id": 203, "pid": 1336753, "tid": 1381210, "ts": 1712360216149.973, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1712360216181.475, "dur": 38.371, + "args": { + "External id": 4729185,"Record function id": 0, "Ev Idx": 3936 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1712360216227.599, "dur": 62.960, + "args": { + "External id": 4729186,"Record function id": 0, "Ev Idx": 3937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1712360216296.577, "dur": 36220.081, + "args": { + "External id": 4729187,"Record function id": 0, "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360216382.816, "dur": 7.148, + "args": { + "External id": 4729188,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360216399.370, "dur": 5.315, + "args": { + "External id": 4729189,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360216419.811, "dur": 35293.585, + "args": { + "External id": 4729190,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360216432.713, "dur": 35272.059, + "args": { + "External id": 4729191,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360216491.795, "dur": 14.924, + "args": { + "External id": 4729192,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360216513.104, "dur": 35154.417, + "args": { + "External id": 4729193,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360216516.029, "dur": 35150.650, + "args": { + "External id": 4729194,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360216519.889, "dur": 5.021, + "args": { + "External id": 4729195,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360216526.793, "dur": 35136.497, + "args": { + "External id": 4729196,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360251801.622, "dur": 9.276, + "args": { + "External id": 4729197,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360251804.940, "dur": 5.603, + "args": { + "External id": 4729198,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360251841.780, "dur": 377.391, + "args": { + "External id": 4729199,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360251867.700, "dur": 346.087, + "args": { + "External id": 4729200,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3951, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360251879.130, "dur": 329.096, + "args": { + "External id": 4729201,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360252239.479, "dur": 2.331, + "args": { + "External id": 4729202,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3953, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252303.043, "dur": 6.834, + "args": { + "External id": 4729203,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252357.665, "dur": 1.448, + "args": { + "External id": 4729204,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252375.870, "dur": 0.927, + "args": { + "External id": 4729205,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252390.831, "dur": 0.829, + "args": { + "External id": 4729206,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252401.991, "dur": 1.126, + "args": { + "External id": 4729207,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252414.509, "dur": 0.981, + "args": { + "External id": 4729208,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252427.152, "dur": 0.837, + "args": { + "External id": 4729209,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252441.576, "dur": 2.036, + "args": { + "External id": 4729210,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252454.582, "dur": 0.794, + "args": { + "External id": 4729211,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360252550.097, "dur": 2670.373, + "args": { + "External id": 4729212,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1712360252568.799, "dur": 1011.074, + "args": { + "External id": 4729213,"Record function id": 0, "Ev Idx": 3964 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1712360252583.407, "dur": 305.604, + "args": { + "External id": 4729214,"Record function id": 0, "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252661.979, "dur": 4.227, + "args": { + "External id": 4729215,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252669.525, "dur": 1.062, + "args": { + "External id": 4729216,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252672.432, "dur": 1.041, + "args": { + "External id": 4729217,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252675.048, "dur": 2.596, + "args": { + "External id": 4729218,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252679.084, "dur": 1.037, + "args": { + "External id": 4729219,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252681.557, "dur": 1.679, + "args": { + "External id": 4729220,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252684.904, "dur": 1.373, + "args": { + "External id": 4729221,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252687.639, "dur": 1.053, + "args": { + "External id": 4729222,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252690.194, "dur": 1.454, + "args": { + "External id": 4729223,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360252693.220, "dur": 1.583, + "args": { + "External id": 4729224,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360252712.078, "dur": 147.166, + "args": { + "External id": 4729225,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360252728.004, "dur": 127.490, + "args": { + "External id": 4729226,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360252746.205, "dur": 11.576, + "args": { + "External id": 4729227,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360252760.638, "dur": 67.402, + "args": { + "External id": 4729228,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360252763.332, "dur": 64.322, + "args": { + "External id": 4729229,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360252767.345, "dur": 6.843, + "args": { + "External id": 4729230,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360252776.145, "dur": 50.986, + "args": { + "External id": 4729231,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3982 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.10", "pid": 1336753, "tid": 1381210, + "ts": 1712360252974.882, "dur": 596.400, + "args": { + "External id": 4729232,"Record function id": 0, "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1712360253034.904, "dur": 523.871, + "args": { + "External id": 4729233,"Record function id": 0, "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360253117.914, "dur": 6.788, + "args": { + "External id": 4729234,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360253140.999, "dur": 29.519, + "args": { + "External id": 4729235,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253146.058, "dur": 1.753, + "args": { + "External id": 4729236,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253150.108, "dur": 0.643, + "args": { + "External id": 4729237,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253152.363, "dur": 0.451, + "args": { + "External id": 4729238,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253154.887, "dur": 0.372, + "args": { + "External id": 4729239,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253156.663, "dur": 0.556, + "args": { + "External id": 4729240,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253158.788, "dur": 0.394, + "args": { + "External id": 4729241,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253160.640, "dur": 2.364, + "args": { + "External id": 4729242,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253164.728, "dur": 0.418, + "args": { + "External id": 4729243,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253166.707, "dur": 0.346, + "args": { + "External id": 4729244,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360253180.951, "dur": 34.286, + "args": { + "External id": 4729245,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360253246.926, "dur": 99.697, + "args": { + "External id": 4729246,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360253257.270, "dur": 4.173, + "args": { + "External id": 4729247,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360253266.767, "dur": 10.442, + "args": { + "External id": 4729248,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360253270.975, "dur": 5.847, + "args": { + "External id": 4729249,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253274.346, "dur": 0.884, + "args": { + "External id": 4729250,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360253283.885, "dur": 26.346, + "args": { + "External id": 4729251,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253285.975, "dur": 0.448, + "args": { + "External id": 4729252,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253288.020, "dur": 0.597, + "args": { + "External id": 4729253,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253290.107, "dur": 0.362, + "args": { + "External id": 4729254,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253291.841, "dur": 2.392, + "args": { + "External id": 4729255,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253295.727, "dur": 0.478, + "args": { + "External id": 4729256,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253297.944, "dur": 0.391, + "args": { + "External id": 4729257,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253299.960, "dur": 0.488, + "args": { + "External id": 4729258,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253302.018, "dur": 0.366, + "args": { + "External id": 4729259,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360253303.994, "dur": 0.359, + "args": { + "External id": 4729260,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360253319.730, "dur": 18.911, + "args": { + "External id": 4729261,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360253392.619, "dur": 105.984, + "args": { + "External id": 4729262,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360253413.476, "dur": 81.276, + "args": { + "External id": 4729263,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4014, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360253422.762, "dur": 68.073, + "args": { + "External id": 4729264,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360253510.694, "dur": 1.875, + "args": { + "External id": 4729265,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4016, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360253587.299, "dur": 1612.371, + "args": { + "External id": 4729266,"Sequence number": 47018788, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4017 + } + }, + { + "ph": "f", "id": 204, "pid": 1336753, "tid": 1381210, "ts": 1712360253587.299, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360253690.298, "dur": 96.638, + "args": { + "External id": 4729267,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360253824.550, "dur": 40.321, + "args": { + "External id": 4729268,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360253881.400, "dur": 48.149, + "args": { + "External id": 4729269,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360253939.075, "dur": 31.378, + "args": { + "External id": 4729270,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360253978.873, "dur": 103.695, + "args": { + "External id": 4729271,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254094.416, "dur": 35.669, + "args": { + "External id": 4729272,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254137.572, "dur": 42.743, + "args": { + "External id": 4729273,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360254204.628, "dur": 23.635, + "args": { + "External id": 4729274,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360254247.346, "dur": 29.844, + "args": { + "External id": 4729275,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360254295.457, "dur": 17.954, + "args": { + "External id": 4729276,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360254330.035, "dur": 15.526, + "args": { + "External id": 4729277,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254354.701, "dur": 28.165, + "args": { + "External id": 4729278,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254386.739, "dur": 32.357, + "args": { + "External id": 4729279,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360254447.849, "dur": 174.142, + "args": { + "External id": 4729280,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360254526.192, "dur": 6.062, + "args": { + "External id": 4729281,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360254534.243, "dur": 2.400, + "args": { + "External id": 4729282,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360254654.895, "dur": 22.081, + "args": { + "External id": 4729283,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360254687.797, "dur": 14.007, + "args": { + "External id": 4729284,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254709.495, "dur": 31.628, + "args": { + "External id": 4729285,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254747.871, "dur": 34.283, + "args": { + "External id": 4729286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254790.812, "dur": 20.236, + "args": { + "External id": 4729287,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254816.962, "dur": 29.583, + "args": { + "External id": 4729288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254853.061, "dur": 19.230, + "args": { + "External id": 4729289,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360254879.992, "dur": 29.930, + "args": { + "External id": 4729290,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360254925.662, "dur": 21.198, + "args": { + "External id": 4729291,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360254962.422, "dur": 60.929, + "args": { + "External id": 4729292,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360255056.828, "dur": 42.629, + "args": { + "External id": 4729293,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360255125.696, "dur": 14.898, + "args": { + "External id": 4729294,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360255153.219, "dur": 17.500, + "args": { + "External id": 4729295,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255246.216, "dur": 15.217, + "args": { + "External id": 4729296,"Record function id": 0, "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255249.368, "dur": 11.199, + "args": { + "External id": 4729297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255253.570, "dur": 6.105, + "args": { + "External id": 4729298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255255.450, "dur": 4.106, + "args": { + "External id": 4729299,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255265.292, "dur": 5.628, + "args": { + "External id": 4729300,"Record function id": 0, "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255266.701, "dur": 3.790, + "args": { + "External id": 4729301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255267.733, "dur": 2.341, + "args": { + "External id": 4729302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255268.954, "dur": 1.017, + "args": { + "External id": 4729303,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255274.267, "dur": 6.535, + "args": { + "External id": 4729304,"Record function id": 0, "Ev Idx": 4055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255275.531, "dur": 4.848, + "args": { + "External id": 4729305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255276.504, "dur": 3.358, + "args": { + "External id": 4729306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255276.968, "dur": 2.836, + "args": { + "External id": 4729307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255284.033, "dur": 4.069, + "args": { + "External id": 4729308,"Record function id": 0, "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255285.206, "dur": 2.495, + "args": { + "External id": 4729309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255285.840, "dur": 1.444, + "args": { + "External id": 4729310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255286.400, "dur": 0.818, + "args": { + "External id": 4729311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255291.261, "dur": 3.349, + "args": { + "External id": 4729312,"Record function id": 0, "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255292.223, "dur": 1.992, + "args": { + "External id": 4729313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255292.712, "dur": 1.060, + "args": { + "External id": 4729314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255292.991, "dur": 0.711, + "args": { + "External id": 4729315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255297.761, "dur": 7.337, + "args": { + "External id": 4729316,"Record function id": 0, "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255298.816, "dur": 5.878, + "args": { + "External id": 4729317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255299.554, "dur": 4.741, + "args": { + "External id": 4729318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255303.463, "dur": 0.672, + "args": { + "External id": 4729319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255308.513, "dur": 3.911, + "args": { + "External id": 4729320,"Record function id": 0, "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255309.513, "dur": 2.514, + "args": { + "External id": 4729321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255310.571, "dur": 1.040, + "args": { + "External id": 4729322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255310.884, "dur": 0.645, + "args": { + "External id": 4729323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255315.500, "dur": 4.120, + "args": { + "External id": 4729324,"Record function id": 0, "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255316.560, "dur": 2.658, + "args": { + "External id": 4729325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255317.553, "dur": 1.250, + "args": { + "External id": 4729326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255318.132, "dur": 0.610, + "args": { + "External id": 4729327,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255322.709, "dur": 3.710, + "args": { + "External id": 4729328,"Record function id": 0, "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360255323.879, "dur": 2.132, + "args": { + "External id": 4729329,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255324.399, "dur": 1.191, + "args": { + "External id": 4729330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360255324.842, "dur": 0.658, + "args": { + "External id": 4729331,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360255330.241, "dur": 36801.029, + "args": { + "External id": 4729332,"Record function id": 0, "Sequence number": 47018787, "Fwd thread id": 1, "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360255331.812, "dur": 36790.356, + "args": { + "External id": 4729333,"Sequence number": 47018787, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4084 + } + }, + { + "ph": "f", "id": 205, "pid": 1336753, "tid": 1381210, "ts": 1712360255331.812, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1712360255363.008, "dur": 36.450, + "args": { + "External id": 4729334,"Record function id": 0, "Ev Idx": 4085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1712360255407.091, "dur": 65.372, + "args": { + "External id": 4729335,"Record function id": 0, "Ev Idx": 4086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1712360255481.278, "dur": 36632.409, + "args": { + "External id": 4729336,"Record function id": 0, "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360255569.554, "dur": 6.483, + "args": { + "External id": 4729337,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360255585.213, "dur": 6.436, + "args": { + "External id": 4729338,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360255609.226, "dur": 35622.432, + "args": { + "External id": 4729339,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360255622.755, "dur": 35598.973, + "args": { + "External id": 4729340,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360255695.200, "dur": 13.834, + "args": { + "External id": 4729341,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360255715.487, "dur": 35466.257, + "args": { + "External id": 4729342,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360255718.309, "dur": 35462.530, + "args": { + "External id": 4729343,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360255722.208, "dur": 5.175, + "args": { + "External id": 4729344,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360255806.350, "dur": 35371.462, + "args": { + "External id": 4729345,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360291322.196, "dur": 9.053, + "args": { + "External id": 4729346,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360291325.446, "dur": 5.449, + "args": { + "External id": 4729347,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360291362.166, "dur": 407.335, + "args": { + "External id": 4729348,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360291386.631, "dur": 377.834, + "args": { + "External id": 4729349,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4100, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360291396.574, "dur": 362.006, + "args": { + "External id": 4729350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360291790.317, "dur": 2.513, + "args": { + "External id": 4729351,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4102, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360291850.481, "dur": 6.660, + "args": { + "External id": 4729352,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360291901.346, "dur": 1.596, + "args": { + "External id": 4729353,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360291918.574, "dur": 2.895, + "args": { + "External id": 4729354,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360291933.126, "dur": 0.979, + "args": { + "External id": 4729355,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360291945.708, "dur": 0.828, + "args": { + "External id": 4729356,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360291956.606, "dur": 0.856, + "args": { + "External id": 4729357,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360291972.761, "dur": 2.720, + "args": { + "External id": 4729358,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292024.966, "dur": 1.886, + "args": { + "External id": 4729359,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292037.943, "dur": 1.161, + "args": { + "External id": 4729360,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360292147.359, "dur": 2668.711, + "args": { + "External id": 4729361,"Record function id": 0, "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1712360292166.861, "dur": 1030.513, + "args": { + "External id": 4729362,"Record function id": 0, "Ev Idx": 4113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1712360292180.474, "dur": 345.483, + "args": { + "External id": 4729363,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292267.047, "dur": 4.633, + "args": { + "External id": 4729364,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292274.596, "dur": 1.377, + "args": { + "External id": 4729365,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292277.601, "dur": 3.358, + "args": { + "External id": 4729366,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292282.697, "dur": 1.075, + "args": { + "External id": 4729367,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292285.228, "dur": 1.463, + "args": { + "External id": 4729368,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292288.499, "dur": 1.107, + "args": { + "External id": 4729369,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292291.127, "dur": 1.452, + "args": { + "External id": 4729370,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292293.895, "dur": 1.367, + "args": { + "External id": 4729371,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292296.523, "dur": 1.277, + "args": { + "External id": 4729372,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360292299.199, "dur": 1.284, + "args": { + "External id": 4729373,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360292317.466, "dur": 175.863, + "args": { + "External id": 4729374,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360292333.204, "dur": 155.624, + "args": { + "External id": 4729375,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360292375.075, "dur": 13.807, + "args": { + "External id": 4729376,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360292392.101, "dur": 68.450, + "args": { + "External id": 4729377,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360292394.927, "dur": 65.318, + "args": { + "External id": 4729378,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292399.164, "dur": 5.764, + "args": { + "External id": 4729379,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360292406.705, "dur": 52.731, + "args": { + "External id": 4729380,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4131 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.9", "pid": 1336753, "tid": 1381210, + "ts": 1712360292613.116, "dur": 576.044, + "args": { + "External id": 4729381,"Record function id": 0, "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1712360292628.300, "dur": 548.811, + "args": { + "External id": 4729382,"Record function id": 0, "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360292686.007, "dur": 4.421, + "args": { + "External id": 4729383,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360292705.438, "dur": 31.552, + "args": { + "External id": 4729384,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292710.022, "dur": 1.307, + "args": { + "External id": 4729385,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292712.894, "dur": 0.419, + "args": { + "External id": 4729386,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292714.970, "dur": 0.352, + "args": { + "External id": 4729387,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292716.731, "dur": 0.439, + "args": { + "External id": 4729388,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292718.738, "dur": 0.506, + "args": { + "External id": 4729389,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292720.345, "dur": 2.125, + "args": { + "External id": 4729390,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292727.406, "dur": 0.423, + "args": { + "External id": 4729391,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292729.151, "dur": 0.469, + "args": { + "External id": 4729392,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292730.960, "dur": 0.473, + "args": { + "External id": 4729393,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360292746.596, "dur": 28.838, + "args": { + "External id": 4729394,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360292804.998, "dur": 95.748, + "args": { + "External id": 4729395,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360292814.802, "dur": 2.945, + "args": { + "External id": 4729396,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360292822.532, "dur": 9.860, + "args": { + "External id": 4729397,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360292826.599, "dur": 5.386, + "args": { + "External id": 4729398,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292830.144, "dur": 0.557, + "args": { + "External id": 4729399,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360292842.277, "dur": 23.208, + "args": { + "External id": 4729400,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292844.206, "dur": 0.509, + "args": { + "External id": 4729401,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292846.297, "dur": 0.481, + "args": { + "External id": 4729402,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292848.402, "dur": 2.171, + "args": { + "External id": 4729403,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292852.012, "dur": 0.347, + "args": { + "External id": 4729404,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292853.733, "dur": 0.546, + "args": { + "External id": 4729405,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292855.435, "dur": 0.337, + "args": { + "External id": 4729406,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292857.156, "dur": 0.424, + "args": { + "External id": 4729407,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292858.944, "dur": 0.335, + "args": { + "External id": 4729408,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360292861.035, "dur": 0.409, + "args": { + "External id": 4729409,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360292875.823, "dur": 17.846, + "args": { + "External id": 4729410,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360292941.575, "dur": 164.009, + "args": { + "External id": 4729411,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360292961.393, "dur": 139.871, + "args": { + "External id": 4729412,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4163, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360292970.178, "dur": 125.832, + "args": { + "External id": 4729413,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360293121.695, "dur": 2.195, + "args": { + "External id": 4729414,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4165, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360293204.725, "dur": 1591.770, + "args": { + "External id": 4729415,"Sequence number": 47018786, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4166 + } + }, + { + "ph": "f", "id": 206, "pid": 1336753, "tid": 1381210, "ts": 1712360293204.725, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360293313.951, "dur": 100.840, + "args": { + "External id": 4729416,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360293451.535, "dur": 36.700, + "args": { + "External id": 4729417,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360293505.439, "dur": 49.837, + "args": { + "External id": 4729418,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360293569.432, "dur": 31.331, + "args": { + "External id": 4729419,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360293607.283, "dur": 44.750, + "args": { + "External id": 4729420,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360293659.405, "dur": 26.978, + "args": { + "External id": 4729421,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360293693.227, "dur": 41.262, + "args": { + "External id": 4729422,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360293756.304, "dur": 20.575, + "args": { + "External id": 4729423,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360293835.800, "dur": 29.433, + "args": { + "External id": 4729424,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360293884.863, "dur": 17.962, + "args": { + "External id": 4729425,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360293917.955, "dur": 14.674, + "args": { + "External id": 4729426,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360293941.630, "dur": 28.260, + "args": { + "External id": 4729427,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360293972.950, "dur": 79.497, + "args": { + "External id": 4729428,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360294102.337, "dur": 174.613, + "args": { + "External id": 4729429,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360294180.977, "dur": 6.116, + "args": { + "External id": 4729430,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360294189.260, "dur": 2.105, + "args": { + "External id": 4729431,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360294310.583, "dur": 22.684, + "args": { + "External id": 4729432,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360294343.520, "dur": 13.285, + "args": { + "External id": 4729433,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360294365.396, "dur": 39.412, + "args": { + "External id": 4729434,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360294411.500, "dur": 34.478, + "args": { + "External id": 4729435,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360294453.753, "dur": 19.506, + "args": { + "External id": 4729436,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360294478.893, "dur": 29.672, + "args": { + "External id": 4729437,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360294514.745, "dur": 23.572, + "args": { + "External id": 4729438,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360294557.095, "dur": 40.756, + "args": { + "External id": 4729439,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360294618.830, "dur": 21.169, + "args": { + "External id": 4729440,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360294656.938, "dur": 26.005, + "args": { + "External id": 4729441,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360294697.136, "dur": 16.203, + "args": { + "External id": 4729442,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360294729.326, "dur": 13.018, + "args": { + "External id": 4729443,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360294753.652, "dur": 15.409, + "args": { + "External id": 4729444,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294838.298, "dur": 14.527, + "args": { + "External id": 4729445,"Record function id": 0, "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294841.415, "dur": 10.429, + "args": { + "External id": 4729446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294845.102, "dur": 5.683, + "args": { + "External id": 4729447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294846.650, "dur": 4.011, + "args": { + "External id": 4729448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294856.779, "dur": 7.359, + "args": { + "External id": 4729449,"Record function id": 0, "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294858.114, "dur": 5.569, + "args": { + "External id": 4729450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294859.001, "dur": 4.208, + "args": { + "External id": 4729451,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294860.072, "dur": 3.058, + "args": { + "External id": 4729452,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294867.651, "dur": 4.900, + "args": { + "External id": 4729453,"Record function id": 0, "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294869.098, "dur": 3.039, + "args": { + "External id": 4729454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294869.811, "dur": 1.891, + "args": { + "External id": 4729455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294870.469, "dur": 1.168, + "args": { + "External id": 4729456,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294875.784, "dur": 4.358, + "args": { + "External id": 4729457,"Record function id": 0, "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294876.907, "dur": 2.823, + "args": { + "External id": 4729458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294877.876, "dur": 1.347, + "args": { + "External id": 4729459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294878.384, "dur": 0.773, + "args": { + "External id": 4729460,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294883.308, "dur": 4.053, + "args": { + "External id": 4729461,"Record function id": 0, "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294884.545, "dur": 2.399, + "args": { + "External id": 4729462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294885.422, "dur": 0.995, + "args": { + "External id": 4729463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294885.709, "dur": 0.640, + "args": { + "External id": 4729464,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294890.517, "dur": 3.478, + "args": { + "External id": 4729465,"Record function id": 0, "Ev Idx": 4216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294891.408, "dur": 2.145, + "args": { + "External id": 4729466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294891.903, "dur": 1.218, + "args": { + "External id": 4729467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294892.437, "dur": 0.565, + "args": { + "External id": 4729468,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294897.296, "dur": 3.618, + "args": { + "External id": 4729469,"Record function id": 0, "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294898.515, "dur": 1.970, + "args": { + "External id": 4729470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294898.984, "dur": 1.075, + "args": { + "External id": 4729471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294899.289, "dur": 0.703, + "args": { + "External id": 4729472,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294904.059, "dur": 3.360, + "args": { + "External id": 4729473,"Record function id": 0, "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294905.029, "dur": 1.973, + "args": { + "External id": 4729474,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294905.511, "dur": 1.048, + "args": { + "External id": 4729475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294905.801, "dur": 0.662, + "args": { + "External id": 4729476,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294910.487, "dur": 5.912, + "args": { + "External id": 4729477,"Record function id": 0, "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360294911.709, "dur": 4.243, + "args": { + "External id": 4729478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294912.412, "dur": 3.091, + "args": { + "External id": 4729479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360294913.006, "dur": 2.376, + "args": { + "External id": 4729480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360294920.115, "dur": 36920.252, + "args": { + "External id": 4729481,"Record function id": 0, "Sequence number": 47018785, "Fwd thread id": 1, "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360294921.306, "dur": 36910.090, + "args": { + "External id": 4729482,"Sequence number": 47018785, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4233 + } + }, + { + "ph": "f", "id": 207, "pid": 1336753, "tid": 1381210, "ts": 1712360294921.306, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1712360294947.243, "dur": 36.753, + "args": { + "External id": 4729483,"Record function id": 0, "Ev Idx": 4234 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1712360295033.671, "dur": 80.851, + "args": { + "External id": 4729484,"Record function id": 0, "Ev Idx": 4235 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1712360295122.020, "dur": 36701.675, + "args": { + "External id": 4729485,"Record function id": 0, "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360295214.447, "dur": 10.229, + "args": { + "External id": 4729486,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360295234.866, "dur": 5.430, + "args": { + "External id": 4729487,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360295256.103, "dur": 35803.273, + "args": { + "External id": 4729488,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360295269.337, "dur": 35780.357, + "args": { + "External id": 4729489,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360295359.058, "dur": 13.889, + "args": { + "External id": 4729490,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360295379.079, "dur": 35633.533, + "args": { + "External id": 4729491,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360295381.609, "dur": 35630.176, + "args": { + "External id": 4729492,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360295385.620, "dur": 5.266, + "args": { + "External id": 4729493,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360295393.018, "dur": 35615.302, + "args": { + "External id": 4729494,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360331163.188, "dur": 9.267, + "args": { + "External id": 4729495,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360331166.100, "dur": 5.849, + "args": { + "External id": 4729496,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360331202.791, "dur": 350.871, + "args": { + "External id": 4729497,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360331227.518, "dur": 321.077, + "args": { + "External id": 4729498,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4249, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360331237.808, "dur": 305.832, + "args": { + "External id": 4729499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360331569.797, "dur": 2.233, + "args": { + "External id": 4729500,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4251, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360331626.553, "dur": 6.674, + "args": { + "External id": 4729501,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360331677.026, "dur": 3.626, + "args": { + "External id": 4729502,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360331695.744, "dur": 1.065, + "args": { + "External id": 4729503,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360331707.620, "dur": 1.041, + "args": { + "External id": 4729504,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360331719.400, "dur": 0.836, + "args": { + "External id": 4729505,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360331729.213, "dur": 3.041, + "args": { + "External id": 4729506,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360331742.503, "dur": 1.014, + "args": { + "External id": 4729507,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360331753.680, "dur": 0.814, + "args": { + "External id": 4729508,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360331763.796, "dur": 1.142, + "args": { + "External id": 4729509,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360331853.970, "dur": 2688.129, + "args": { + "External id": 4729510,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1712360331873.688, "dur": 1011.822, + "args": { + "External id": 4729511,"Record function id": 0, "Ev Idx": 4262 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1712360331888.742, "dur": 379.657, + "args": { + "External id": 4729512,"Record function id": 0, "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360331970.210, "dur": 6.156, + "args": { + "External id": 4729513,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360331979.707, "dur": 0.905, + "args": { + "External id": 4729514,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360332025.009, "dur": 1.491, + "args": { + "External id": 4729515,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360332028.719, "dur": 1.047, + "args": { + "External id": 4729516,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360332031.268, "dur": 1.031, + "args": { + "External id": 4729517,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360332033.855, "dur": 1.066, + "args": { + "External id": 4729518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360332038.337, "dur": 0.992, + "args": { + "External id": 4729519,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360332040.683, "dur": 0.907, + "args": { + "External id": 4729520,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360332043.234, "dur": 3.018, + "args": { + "External id": 4729521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360332047.667, "dur": 0.909, + "args": { + "External id": 4729522,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360332084.350, "dur": 151.824, + "args": { + "External id": 4729523,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360332101.111, "dur": 130.900, + "args": { + "External id": 4729524,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360332120.027, "dur": 13.573, + "args": { + "External id": 4729525,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360332136.637, "dur": 68.316, + "args": { + "External id": 4729526,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360332139.004, "dur": 65.625, + "args": { + "External id": 4729527,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332142.616, "dur": 6.126, + "args": { + "External id": 4729528,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360332152.391, "dur": 51.515, + "args": { + "External id": 4729529,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4280 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.8", "pid": 1336753, "tid": 1381210, + "ts": 1712360332360.388, "dur": 517.556, + "args": { + "External id": 4729530,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1712360332378.231, "dur": 488.399, + "args": { + "External id": 4729531,"Record function id": 0, "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360332437.690, "dur": 4.542, + "args": { + "External id": 4729532,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360332461.146, "dur": 25.526, + "args": { + "External id": 4729533,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332465.197, "dur": 1.606, + "args": { + "External id": 4729534,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332468.629, "dur": 0.820, + "args": { + "External id": 4729535,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332470.459, "dur": 0.407, + "args": { + "External id": 4729536,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332472.190, "dur": 1.803, + "args": { + "External id": 4729537,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332475.235, "dur": 0.399, + "args": { + "External id": 4729538,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332477.356, "dur": 0.248, + "args": { + "External id": 4729539,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332478.829, "dur": 0.280, + "args": { + "External id": 4729540,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332480.393, "dur": 0.359, + "args": { + "External id": 4729541,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332482.116, "dur": 0.256, + "args": { + "External id": 4729542,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360332496.702, "dur": 28.151, + "args": { + "External id": 4729543,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360332554.100, "dur": 93.104, + "args": { + "External id": 4729544,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360332563.471, "dur": 2.592, + "args": { + "External id": 4729545,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360332571.140, "dur": 9.673, + "args": { + "External id": 4729546,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360332575.167, "dur": 5.203, + "args": { + "External id": 4729547,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332578.687, "dur": 0.553, + "args": { + "External id": 4729548,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360332587.521, "dur": 23.928, + "args": { + "External id": 4729549,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332589.540, "dur": 2.342, + "args": { + "External id": 4729550,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332593.394, "dur": 0.621, + "args": { + "External id": 4729551,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332595.250, "dur": 0.414, + "args": { + "External id": 4729552,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332597.229, "dur": 0.422, + "args": { + "External id": 4729553,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332598.927, "dur": 0.568, + "args": { + "External id": 4729554,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332600.966, "dur": 0.419, + "args": { + "External id": 4729555,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332603.030, "dur": 0.425, + "args": { + "External id": 4729556,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332604.647, "dur": 0.459, + "args": { + "External id": 4729557,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360332606.702, "dur": 2.384, + "args": { + "External id": 4729558,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360332622.595, "dur": 17.869, + "args": { + "External id": 4729559,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360332694.231, "dur": 112.499, + "args": { + "External id": 4729560,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360332724.747, "dur": 78.769, + "args": { + "External id": 4729561,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4312, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360332733.102, "dur": 66.474, + "args": { + "External id": 4729562,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360332822.367, "dur": 1.971, + "args": { + "External id": 4729563,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4314, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360332892.302, "dur": 1627.832, + "args": { + "External id": 4729564,"Sequence number": 47018784, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4315 + } + }, + { + "ph": "f", "id": 208, "pid": 1336753, "tid": 1381210, "ts": 1712360332892.302, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360333042.668, "dur": 117.599, + "args": { + "External id": 4729565,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360333203.850, "dur": 38.504, + "args": { + "External id": 4729566,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360333260.908, "dur": 48.120, + "args": { + "External id": 4729567,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360333318.121, "dur": 31.896, + "args": { + "External id": 4729568,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360333356.302, "dur": 45.221, + "args": { + "External id": 4729569,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360333407.773, "dur": 27.600, + "args": { + "External id": 4729570,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360333444.542, "dur": 41.168, + "args": { + "External id": 4729571,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360333508.605, "dur": 21.307, + "args": { + "External id": 4729572,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360333549.327, "dur": 26.357, + "args": { + "External id": 4729573,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360333595.918, "dur": 17.673, + "args": { + "External id": 4729574,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360333629.540, "dur": 14.528, + "args": { + "External id": 4729575,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360333652.939, "dur": 26.966, + "args": { + "External id": 4729576,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360333683.064, "dur": 32.450, + "args": { + "External id": 4729577,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360333741.668, "dur": 159.547, + "args": { + "External id": 4729578,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360333813.778, "dur": 5.202, + "args": { + "External id": 4729579,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360333820.952, "dur": 1.920, + "args": { + "External id": 4729580,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360333932.543, "dur": 23.250, + "args": { + "External id": 4729581,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360333967.104, "dur": 13.369, + "args": { + "External id": 4729582,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360334033.754, "dur": 61.139, + "args": { + "External id": 4729583,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360334105.625, "dur": 39.817, + "args": { + "External id": 4729584,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360334152.238, "dur": 19.599, + "args": { + "External id": 4729585,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360334179.126, "dur": 32.100, + "args": { + "External id": 4729586,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360334217.592, "dur": 19.472, + "args": { + "External id": 4729587,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360334246.085, "dur": 33.651, + "args": { + "External id": 4729588,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360334302.368, "dur": 26.340, + "args": { + "External id": 4729589,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360334360.719, "dur": 34.515, + "args": { + "External id": 4729590,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360334412.174, "dur": 17.049, + "args": { + "External id": 4729591,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360334445.952, "dur": 14.290, + "args": { + "External id": 4729592,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360334475.342, "dur": 16.124, + "args": { + "External id": 4729593,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334564.151, "dur": 16.965, + "args": { + "External id": 4729594,"Record function id": 0, "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334567.495, "dur": 12.703, + "args": { + "External id": 4729595,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334571.780, "dur": 7.529, + "args": { + "External id": 4729596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334573.590, "dur": 5.579, + "args": { + "External id": 4729597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334588.391, "dur": 5.262, + "args": { + "External id": 4729598,"Record function id": 0, "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334589.687, "dur": 3.513, + "args": { + "External id": 4729599,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334590.582, "dur": 2.096, + "args": { + "External id": 4729600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334591.559, "dur": 1.054, + "args": { + "External id": 4729601,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334597.020, "dur": 4.385, + "args": { + "External id": 4729602,"Record function id": 0, "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334598.215, "dur": 2.772, + "args": { + "External id": 4729603,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334599.167, "dur": 1.349, + "args": { + "External id": 4729604,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334599.454, "dur": 1.001, + "args": { + "External id": 4729605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334604.600, "dur": 3.716, + "args": { + "External id": 4729606,"Record function id": 0, "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334605.536, "dur": 2.358, + "args": { + "External id": 4729607,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334606.096, "dur": 1.266, + "args": { + "External id": 4729608,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334606.555, "dur": 0.743, + "args": { + "External id": 4729609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334611.439, "dur": 3.745, + "args": { + "External id": 4729610,"Record function id": 0, "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334612.581, "dur": 2.188, + "args": { + "External id": 4729611,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334613.246, "dur": 1.116, + "args": { + "External id": 4729612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334613.546, "dur": 0.747, + "args": { + "External id": 4729613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334618.402, "dur": 4.060, + "args": { + "External id": 4729614,"Record function id": 0, "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334619.569, "dur": 2.412, + "args": { + "External id": 4729615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334620.237, "dur": 1.282, + "args": { + "External id": 4729616,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334620.735, "dur": 0.674, + "args": { + "External id": 4729617,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334625.778, "dur": 3.516, + "args": { + "External id": 4729618,"Record function id": 0, "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334626.749, "dur": 2.107, + "args": { + "External id": 4729619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334627.346, "dur": 1.072, + "args": { + "External id": 4729620,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334627.640, "dur": 0.714, + "args": { + "External id": 4729621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334632.307, "dur": 5.818, + "args": { + "External id": 4729622,"Record function id": 0, "Ev Idx": 4373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334633.405, "dur": 4.302, + "args": { + "External id": 4729623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334634.251, "dur": 3.026, + "args": { + "External id": 4729624,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334634.558, "dur": 2.646, + "args": { + "External id": 4729625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334641.283, "dur": 7.517, + "args": { + "External id": 4729626,"Record function id": 0, "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360334642.706, "dur": 5.657, + "args": { + "External id": 4729627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334646.398, "dur": 1.564, + "args": { + "External id": 4729628,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360334646.809, "dur": 1.038, + "args": { + "External id": 4729629,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360334652.343, "dur": 38236.400, + "args": { + "External id": 4729630,"Record function id": 0, "Sequence number": 47018783, "Fwd thread id": 1, "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360334653.512, "dur": 38227.394, + "args": { + "External id": 4729631,"Sequence number": 47018783, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4382 + } + }, + { + "ph": "f", "id": 209, "pid": 1336753, "tid": 1381210, "ts": 1712360334653.512, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1712360334682.155, "dur": 35.986, + "args": { + "External id": 4729632,"Record function id": 0, "Ev Idx": 4383 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1712360334725.833, "dur": 61.237, + "args": { + "External id": 4729633,"Record function id": 0, "Ev Idx": 4384 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1712360334793.146, "dur": 38079.909, + "args": { + "External id": 4729634,"Record function id": 0, "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360334877.713, "dur": 9.201, + "args": { + "External id": 4729635,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360334896.132, "dur": 4.843, + "args": { + "External id": 4729636,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360334915.171, "dur": 37232.621, + "args": { + "External id": 4729637,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360334928.148, "dur": 37210.814, + "args": { + "External id": 4729638,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360335036.459, "dur": 14.061, + "args": { + "External id": 4729639,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360335060.661, "dur": 37040.948, + "args": { + "External id": 4729640,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360335063.197, "dur": 37037.592, + "args": { + "External id": 4729641,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360335081.530, "dur": 7.316, + "args": { + "External id": 4729642,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360335090.776, "dur": 37006.807, + "args": { + "External id": 4729643,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360372237.105, "dur": 8.139, + "args": { + "External id": 4729644,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360372239.883, "dur": 4.997, + "args": { + "External id": 4729645,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360372278.278, "dur": 323.991, + "args": { + "External id": 4729646,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360372307.321, "dur": 290.433, + "args": { + "External id": 4729647,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4398, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360372318.689, "dur": 274.058, + "args": { + "External id": 4729648,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360372622.338, "dur": 2.379, + "args": { + "External id": 4729649,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4400, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360372675.551, "dur": 6.740, + "args": { + "External id": 4729650,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360372725.987, "dur": 1.378, + "args": { + "External id": 4729651,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360372742.927, "dur": 1.035, + "args": { + "External id": 4729652,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360372755.761, "dur": 0.759, + "args": { + "External id": 4729653,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360372768.134, "dur": 0.960, + "args": { + "External id": 4729654,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360372780.973, "dur": 0.961, + "args": { + "External id": 4729655,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360372792.659, "dur": 0.711, + "args": { + "External id": 4729656,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360372803.632, "dur": 0.771, + "args": { + "External id": 4729657,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360372814.429, "dur": 0.938, + "args": { + "External id": 4729658,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360372902.007, "dur": 2714.010, + "args": { + "External id": 4729659,"Record function id": 0, "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1712360372920.909, "dur": 1026.327, + "args": { + "External id": 4729660,"Record function id": 0, "Ev Idx": 4411 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1712360372935.365, "dur": 372.684, + "args": { + "External id": 4729661,"Record function id": 0, "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373059.146, "dur": 19.965, + "args": { + "External id": 4729662,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373084.962, "dur": 1.756, + "args": { + "External id": 4729663,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373088.308, "dur": 1.096, + "args": { + "External id": 4729664,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373091.051, "dur": 0.984, + "args": { + "External id": 4729665,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373095.100, "dur": 1.257, + "args": { + "External id": 4729666,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373097.808, "dur": 0.754, + "args": { + "External id": 4729667,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373100.115, "dur": 1.098, + "args": { + "External id": 4729668,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373103.130, "dur": 2.417, + "args": { + "External id": 4729669,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373108.784, "dur": 0.896, + "args": { + "External id": 4729670,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360373111.124, "dur": 1.262, + "args": { + "External id": 4729671,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360373131.406, "dur": 147.862, + "args": { + "External id": 4729672,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360373147.566, "dur": 127.141, + "args": { + "External id": 4729673,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360373167.304, "dur": 12.380, + "args": { + "External id": 4729674,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360373182.272, "dur": 66.823, + "args": { + "External id": 4729675,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360373184.629, "dur": 64.154, + "args": { + "External id": 4729676,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373189.073, "dur": 5.540, + "args": { + "External id": 4729677,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360373197.732, "dur": 50.112, + "args": { + "External id": 4729678,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4429 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.7", "pid": 1336753, "tid": 1381210, + "ts": 1712360373406.337, "dur": 532.608, + "args": { + "External id": 4729679,"Record function id": 0, "Ev Idx": 4430 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1712360373423.922, "dur": 502.731, + "args": { + "External id": 4729680,"Record function id": 0, "Ev Idx": 4431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360373485.953, "dur": 4.341, + "args": { + "External id": 4729681,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360373505.570, "dur": 28.607, + "args": { + "External id": 4729682,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373509.917, "dur": 2.723, + "args": { + "External id": 4729683,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373514.701, "dur": 0.595, + "args": { + "External id": 4729684,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373516.921, "dur": 2.472, + "args": { + "External id": 4729685,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373521.284, "dur": 0.759, + "args": { + "External id": 4729686,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373523.370, "dur": 0.710, + "args": { + "External id": 4729687,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373525.378, "dur": 0.772, + "args": { + "External id": 4729688,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373527.790, "dur": 0.346, + "args": { + "External id": 4729689,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373529.543, "dur": 0.271, + "args": { + "External id": 4729690,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373531.329, "dur": 0.372, + "args": { + "External id": 4729691,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360373543.969, "dur": 29.441, + "args": { + "External id": 4729692,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360373603.373, "dur": 99.503, + "args": { + "External id": 4729693,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360373611.991, "dur": 3.370, + "args": { + "External id": 4729694,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360373620.384, "dur": 11.193, + "args": { + "External id": 4729695,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360373624.358, "dur": 6.832, + "args": { + "External id": 4729696,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373627.638, "dur": 2.415, + "args": { + "External id": 4729697,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360373638.707, "dur": 24.536, + "args": { + "External id": 4729698,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373640.684, "dur": 0.678, + "args": { + "External id": 4729699,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373642.772, "dur": 0.454, + "args": { + "External id": 4729700,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373644.651, "dur": 0.370, + "args": { + "External id": 4729701,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373646.430, "dur": 0.597, + "args": { + "External id": 4729702,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373648.609, "dur": 0.545, + "args": { + "External id": 4729703,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373650.602, "dur": 0.412, + "args": { + "External id": 4729704,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373652.376, "dur": 0.326, + "args": { + "External id": 4729705,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373653.872, "dur": 2.004, + "args": { + "External id": 4729706,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360373657.485, "dur": 0.425, + "args": { + "External id": 4729707,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360373677.062, "dur": 19.029, + "args": { + "External id": 4729708,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360373745.736, "dur": 116.896, + "args": { + "External id": 4729709,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360373773.706, "dur": 85.588, + "args": { + "External id": 4729710,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4461, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360373782.586, "dur": 69.294, + "args": { + "External id": 4729711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360373877.928, "dur": 1.843, + "args": { + "External id": 4729712,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4463, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360373954.668, "dur": 1642.164, + "args": { + "External id": 4729713,"Sequence number": 47018782, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4464 + } + }, + { + "ph": "f", "id": 210, "pid": 1336753, "tid": 1381210, "ts": 1712360373954.668, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360374141.412, "dur": 103.754, + "args": { + "External id": 4729714,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360374286.687, "dur": 37.250, + "args": { + "External id": 4729715,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360374341.544, "dur": 44.829, + "args": { + "External id": 4729716,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360374396.090, "dur": 30.772, + "args": { + "External id": 4729717,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360374432.471, "dur": 43.693, + "args": { + "External id": 4729718,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360374483.109, "dur": 28.158, + "args": { + "External id": 4729719,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360374519.887, "dur": 41.699, + "args": { + "External id": 4729720,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360374583.608, "dur": 21.011, + "args": { + "External id": 4729721,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360374623.128, "dur": 27.342, + "args": { + "External id": 4729722,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360374671.460, "dur": 17.554, + "args": { + "External id": 4729723,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360374703.605, "dur": 17.462, + "args": { + "External id": 4729724,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360374729.933, "dur": 26.159, + "args": { + "External id": 4729725,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360374759.047, "dur": 35.171, + "args": { + "External id": 4729726,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360374821.472, "dur": 205.287, + "args": { + "External id": 4729727,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360374896.755, "dur": 6.296, + "args": { + "External id": 4729728,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360374904.697, "dur": 2.249, + "args": { + "External id": 4729729,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360375083.430, "dur": 27.867, + "args": { + "External id": 4729730,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360375125.117, "dur": 14.550, + "args": { + "External id": 4729731,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360375151.842, "dur": 49.777, + "args": { + "External id": 4729732,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360375207.605, "dur": 35.292, + "args": { + "External id": 4729733,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360375248.784, "dur": 19.949, + "args": { + "External id": 4729734,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360375273.099, "dur": 29.623, + "args": { + "External id": 4729735,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360375309.508, "dur": 18.358, + "args": { + "External id": 4729736,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360375335.551, "dur": 28.843, + "args": { + "External id": 4729737,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360375384.005, "dur": 20.316, + "args": { + "External id": 4729738,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360375426.595, "dur": 32.569, + "args": { + "External id": 4729739,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360375483.998, "dur": 21.721, + "args": { + "External id": 4729740,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360375523.124, "dur": 12.757, + "args": { + "External id": 4729741,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360375546.784, "dur": 15.639, + "args": { + "External id": 4729742,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375640.939, "dur": 15.260, + "args": { + "External id": 4729743,"Record function id": 0, "Ev Idx": 4494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375643.779, "dur": 11.487, + "args": { + "External id": 4729744,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375648.551, "dur": 5.821, + "args": { + "External id": 4729745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375649.901, "dur": 4.385, + "args": { + "External id": 4729746,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375660.199, "dur": 4.864, + "args": { + "External id": 4729747,"Record function id": 0, "Ev Idx": 4498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375661.353, "dur": 3.289, + "args": { + "External id": 4729748,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375662.587, "dur": 1.525, + "args": { + "External id": 4729749,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375663.257, "dur": 0.788, + "args": { + "External id": 4729750,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375668.475, "dur": 4.080, + "args": { + "External id": 4729751,"Record function id": 0, "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375669.772, "dur": 2.383, + "args": { + "External id": 4729752,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375670.490, "dur": 1.201, + "args": { + "External id": 4729753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375670.945, "dur": 0.682, + "args": { + "External id": 4729754,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375675.793, "dur": 4.173, + "args": { + "External id": 4729755,"Record function id": 0, "Ev Idx": 4506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375676.818, "dur": 2.711, + "args": { + "External id": 4729756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375677.494, "dur": 1.308, + "args": { + "External id": 4729757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375677.996, "dur": 0.705, + "args": { + "External id": 4729758,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375683.135, "dur": 6.941, + "args": { + "External id": 4729759,"Record function id": 0, "Ev Idx": 4510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375684.341, "dur": 2.287, + "args": { + "External id": 4729760,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375684.829, "dur": 1.144, + "args": { + "External id": 4729761,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375685.306, "dur": 0.571, + "args": { + "External id": 4729762,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375693.186, "dur": 3.699, + "args": { + "External id": 4729763,"Record function id": 0, "Ev Idx": 4514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375694.168, "dur": 2.294, + "args": { + "External id": 4729764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375694.849, "dur": 1.145, + "args": { + "External id": 4729765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375695.132, "dur": 0.774, + "args": { + "External id": 4729766,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375700.235, "dur": 5.560, + "args": { + "External id": 4729767,"Record function id": 0, "Ev Idx": 4518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375701.409, "dur": 3.986, + "args": { + "External id": 4729768,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375701.881, "dur": 3.075, + "args": { + "External id": 4729769,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375702.473, "dur": 2.396, + "args": { + "External id": 4729770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375709.019, "dur": 3.559, + "args": { + "External id": 4729771,"Record function id": 0, "Ev Idx": 4522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375710.096, "dur": 2.052, + "args": { + "External id": 4729772,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375710.600, "dur": 1.139, + "args": { + "External id": 4729773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375710.859, "dur": 0.785, + "args": { + "External id": 4729774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375715.620, "dur": 5.139, + "args": { + "External id": 4729775,"Record function id": 0, "Ev Idx": 4526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360375716.787, "dur": 3.552, + "args": { + "External id": 4729776,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375717.251, "dur": 2.663, + "args": { + "External id": 4729777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360375719.243, "dur": 0.604, + "args": { + "External id": 4729778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360375724.431, "dur": 36332.328, + "args": { + "External id": 4729779,"Record function id": 0, "Sequence number": 47018781, "Fwd thread id": 1, "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360375725.789, "dur": 36322.292, + "args": { + "External id": 4729780,"Sequence number": 47018781, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4531 + } + }, + { + "ph": "f", "id": 211, "pid": 1336753, "tid": 1381210, "ts": 1712360375725.789, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1712360375755.630, "dur": 34.510, + "args": { + "External id": 4729781,"Record function id": 0, "Ev Idx": 4532 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1712360375797.309, "dur": 64.462, + "args": { + "External id": 4729782,"Record function id": 0, "Ev Idx": 4533 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1712360375867.175, "dur": 36171.824, + "args": { + "External id": 4729783,"Record function id": 0, "Ev Idx": 4534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360375955.290, "dur": 6.409, + "args": { + "External id": 4729784,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360375970.181, "dur": 4.568, + "args": { + "External id": 4729785,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360376031.112, "dur": 35167.857, + "args": { + "External id": 4729786,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360376045.531, "dur": 35144.649, + "args": { + "External id": 4729787,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360376122.834, "dur": 14.526, + "args": { + "External id": 4729788,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360376143.603, "dur": 35007.577, + "args": { + "External id": 4729789,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360376146.389, "dur": 35004.111, + "args": { + "External id": 4729790,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360376150.375, "dur": 6.664, + "args": { + "External id": 4729791,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360376158.740, "dur": 34988.403, + "args": { + "External id": 4729792,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360411282.526, "dur": 8.208, + "args": { + "External id": 4729793,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360411285.245, "dur": 5.130, + "args": { + "External id": 4729794,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360411319.548, "dur": 408.214, + "args": { + "External id": 4729795,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360411347.286, "dur": 375.809, + "args": { + "External id": 4729796,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4547, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360411357.061, "dur": 360.141, + "args": { + "External id": 4729797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360411746.361, "dur": 2.289, + "args": { + "External id": 4729798,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4549, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360411801.360, "dur": 8.535, + "args": { + "External id": 4729799,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360411851.014, "dur": 1.461, + "args": { + "External id": 4729800,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360411867.741, "dur": 1.061, + "args": { + "External id": 4729801,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360411880.001, "dur": 0.895, + "args": { + "External id": 4729802,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360411894.980, "dur": 2.645, + "args": { + "External id": 4729803,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360411907.337, "dur": 0.759, + "args": { + "External id": 4729804,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360411919.545, "dur": 0.982, + "args": { + "External id": 4729805,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360411931.242, "dur": 0.982, + "args": { + "External id": 4729806,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360411941.770, "dur": 2.481, + "args": { + "External id": 4729807,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360412086.525, "dur": 2686.536, + "args": { + "External id": 4729808,"Record function id": 0, "Ev Idx": 4559 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1712360412108.757, "dur": 1087.506, + "args": { + "External id": 4729809,"Record function id": 0, "Ev Idx": 4560 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1712360412124.648, "dur": 304.879, + "args": { + "External id": 4729810,"Record function id": 0, "Ev Idx": 4561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412204.662, "dur": 4.918, + "args": { + "External id": 4729811,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412212.784, "dur": 1.087, + "args": { + "External id": 4729812,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412216.784, "dur": 1.012, + "args": { + "External id": 4729813,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412219.554, "dur": 1.096, + "args": { + "External id": 4729814,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412222.256, "dur": 0.887, + "args": { + "External id": 4729815,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412224.494, "dur": 0.925, + "args": { + "External id": 4729816,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412228.384, "dur": 2.855, + "args": { + "External id": 4729817,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412232.696, "dur": 1.260, + "args": { + "External id": 4729818,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412235.413, "dur": 0.798, + "args": { + "External id": 4729819,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360412237.781, "dur": 0.762, + "args": { + "External id": 4729820,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360412257.033, "dur": 143.561, + "args": { + "External id": 4729821,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360412273.624, "dur": 122.846, + "args": { + "External id": 4729822,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360412290.752, "dur": 12.092, + "args": { + "External id": 4729823,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360412305.593, "dur": 64.513, + "args": { + "External id": 4729824,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360412308.039, "dur": 61.749, + "args": { + "External id": 4729825,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412312.257, "dur": 5.686, + "args": { + "External id": 4729826,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360412319.648, "dur": 49.674, + "args": { + "External id": 4729827,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4578 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.6", "pid": 1336753, "tid": 1381210, + "ts": 1712360412518.561, "dur": 669.861, + "args": { + "External id": 4729828,"Record function id": 0, "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1712360412533.582, "dur": 638.845, + "args": { + "External id": 4729829,"Record function id": 0, "Ev Idx": 4580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360412589.818, "dur": 4.302, + "args": { + "External id": 4729830,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360412609.795, "dur": 28.207, + "args": { + "External id": 4729831,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412614.184, "dur": 2.008, + "args": { + "External id": 4729832,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412618.621, "dur": 2.366, + "args": { + "External id": 4729833,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412622.347, "dur": 0.472, + "args": { + "External id": 4729834,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412625.506, "dur": 0.379, + "args": { + "External id": 4729835,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412626.989, "dur": 0.460, + "args": { + "External id": 4729836,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412628.882, "dur": 0.405, + "args": { + "External id": 4729837,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412630.766, "dur": 0.514, + "args": { + "External id": 4729838,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412632.544, "dur": 0.650, + "args": { + "External id": 4729839,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412634.786, "dur": 0.717, + "args": { + "External id": 4729840,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360412647.864, "dur": 29.309, + "args": { + "External id": 4729841,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360412706.748, "dur": 173.996, + "args": { + "External id": 4729842,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360412715.930, "dur": 5.074, + "args": { + "External id": 4729843,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360412726.112, "dur": 9.816, + "args": { + "External id": 4729844,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360412730.064, "dur": 5.482, + "args": { + "External id": 4729845,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412734.010, "dur": 0.570, + "args": { + "External id": 4729846,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360412742.851, "dur": 25.812, + "args": { + "External id": 4729847,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412744.964, "dur": 0.680, + "args": { + "External id": 4729848,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412747.491, "dur": 0.326, + "args": { + "External id": 4729849,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412748.901, "dur": 0.493, + "args": { + "External id": 4729850,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412750.974, "dur": 0.362, + "args": { + "External id": 4729851,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412752.996, "dur": 0.452, + "args": { + "External id": 4729852,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412754.943, "dur": 0.360, + "args": { + "External id": 4729853,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412756.716, "dur": 1.903, + "args": { + "External id": 4729854,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412760.083, "dur": 0.532, + "args": { + "External id": 4729855,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360412761.952, "dur": 0.418, + "args": { + "External id": 4729856,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360412852.333, "dur": 20.700, + "args": { + "External id": 4729857,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360412922.172, "dur": 170.281, + "args": { + "External id": 4729858,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360412948.382, "dur": 140.046, + "args": { + "External id": 4729859,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4610, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360412956.970, "dur": 125.300, + "args": { + "External id": 4729860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360413110.863, "dur": 2.142, + "args": { + "External id": 4729861,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4612, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360413203.766, "dur": 1546.302, + "args": { + "External id": 4729862,"Sequence number": 47018780, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4613 + } + }, + { + "ph": "f", "id": 212, "pid": 1336753, "tid": 1381210, "ts": 1712360413203.766, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360413320.029, "dur": 101.188, + "args": { + "External id": 4729863,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360413460.743, "dur": 37.851, + "args": { + "External id": 4729864,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360413516.953, "dur": 46.641, + "args": { + "External id": 4729865,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360413573.083, "dur": 30.617, + "args": { + "External id": 4729866,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360413615.330, "dur": 44.804, + "args": { + "External id": 4729867,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360413668.763, "dur": 26.271, + "args": { + "External id": 4729868,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360413702.248, "dur": 41.160, + "args": { + "External id": 4729869,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360413765.459, "dur": 21.624, + "args": { + "External id": 4729870,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360413805.588, "dur": 26.175, + "args": { + "External id": 4729871,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360413851.021, "dur": 18.262, + "args": { + "External id": 4729872,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360413881.720, "dur": 12.851, + "args": { + "External id": 4729873,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360413904.252, "dur": 27.666, + "args": { + "External id": 4729874,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360413934.952, "dur": 32.024, + "args": { + "External id": 4729875,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360414033.509, "dur": 197.684, + "args": { + "External id": 4729876,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360414134.648, "dur": 6.627, + "args": { + "External id": 4729877,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360414143.293, "dur": 4.177, + "args": { + "External id": 4729878,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360414270.903, "dur": 24.098, + "args": { + "External id": 4729879,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360414305.778, "dur": 13.415, + "args": { + "External id": 4729880,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360414326.356, "dur": 39.137, + "args": { + "External id": 4729881,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360414370.977, "dur": 35.281, + "args": { + "External id": 4729882,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360414412.331, "dur": 18.668, + "args": { + "External id": 4729883,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360414436.901, "dur": 28.881, + "args": { + "External id": 4729884,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360414471.048, "dur": 18.603, + "args": { + "External id": 4729885,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360414497.488, "dur": 28.506, + "args": { + "External id": 4729886,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360414545.388, "dur": 19.990, + "args": { + "External id": 4729887,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360414582.674, "dur": 35.146, + "args": { + "External id": 4729888,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360414644.037, "dur": 19.260, + "args": { + "External id": 4729889,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360414678.909, "dur": 13.426, + "args": { + "External id": 4729890,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360414708.313, "dur": 16.125, + "args": { + "External id": 4729891,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414795.039, "dur": 14.607, + "args": { + "External id": 4729892,"Record function id": 0, "Ev Idx": 4643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414798.147, "dur": 10.505, + "args": { + "External id": 4729893,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414802.266, "dur": 5.479, + "args": { + "External id": 4729894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414803.723, "dur": 3.894, + "args": { + "External id": 4729895,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414816.779, "dur": 4.155, + "args": { + "External id": 4729896,"Record function id": 0, "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414818.096, "dur": 2.429, + "args": { + "External id": 4729897,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414818.808, "dur": 1.186, + "args": { + "External id": 4729898,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414819.215, "dur": 0.673, + "args": { + "External id": 4729899,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414824.248, "dur": 4.684, + "args": { + "External id": 4729900,"Record function id": 0, "Ev Idx": 4651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414825.373, "dur": 3.108, + "args": { + "External id": 4729901,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414826.059, "dur": 1.703, + "args": { + "External id": 4729902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414826.770, "dur": 0.897, + "args": { + "External id": 4729903,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414832.172, "dur": 3.814, + "args": { + "External id": 4729904,"Record function id": 0, "Ev Idx": 4655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414833.482, "dur": 2.099, + "args": { + "External id": 4729905,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414834.180, "dur": 1.011, + "args": { + "External id": 4729906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414834.487, "dur": 0.618, + "args": { + "External id": 4729907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414839.133, "dur": 4.939, + "args": { + "External id": 4729908,"Record function id": 0, "Ev Idx": 4659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414840.216, "dur": 3.419, + "args": { + "External id": 4729909,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414840.678, "dur": 2.564, + "args": { + "External id": 4729910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414840.959, "dur": 2.222, + "args": { + "External id": 4729911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414847.382, "dur": 3.583, + "args": { + "External id": 4729912,"Record function id": 0, "Ev Idx": 4663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414848.292, "dur": 2.248, + "args": { + "External id": 4729913,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414848.764, "dur": 1.315, + "args": { + "External id": 4729914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414849.127, "dur": 0.883, + "args": { + "External id": 4729915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414854.158, "dur": 4.925, + "args": { + "External id": 4729916,"Record function id": 0, "Ev Idx": 4667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414855.300, "dur": 3.379, + "args": { + "External id": 4729917,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414855.743, "dur": 2.519, + "args": { + "External id": 4729918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414857.480, "dur": 0.693, + "args": { + "External id": 4729919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414862.197, "dur": 3.455, + "args": { + "External id": 4729920,"Record function id": 0, "Ev Idx": 4671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414863.393, "dur": 1.830, + "args": { + "External id": 4729921,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414863.880, "dur": 0.960, + "args": { + "External id": 4729922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414864.187, "dur": 0.586, + "args": { + "External id": 4729923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414868.755, "dur": 6.910, + "args": { + "External id": 4729924,"Record function id": 0, "Ev Idx": 4675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360414869.992, "dur": 5.274, + "args": { + "External id": 4729925,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414873.753, "dur": 1.125, + "args": { + "External id": 4729926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360414874.010, "dur": 0.802, + "args": { + "External id": 4729927,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360414879.425, "dur": 36862.249, + "args": { + "External id": 4729928,"Record function id": 0, "Sequence number": 47018779, "Fwd thread id": 1, "Ev Idx": 4679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360414880.827, "dur": 36852.328, + "args": { + "External id": 4729929,"Sequence number": 47018779, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4680 + } + }, + { + "ph": "f", "id": 213, "pid": 1336753, "tid": 1381210, "ts": 1712360414880.827, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1712360414908.450, "dur": 38.068, + "args": { + "External id": 4729930,"Record function id": 0, "Ev Idx": 4681 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1712360414953.944, "dur": 125.386, + "args": { + "External id": 4729931,"Record function id": 0, "Ev Idx": 4682 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1712360415089.041, "dur": 36636.270, + "args": { + "External id": 4729932,"Record function id": 0, "Ev Idx": 4683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360415177.683, "dur": 7.226, + "args": { + "External id": 4729933,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360415194.982, "dur": 5.184, + "args": { + "External id": 4729934,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360415215.504, "dur": 35690.990, + "args": { + "External id": 4729935,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360415228.618, "dur": 35668.987, + "args": { + "External id": 4729936,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360415287.118, "dur": 13.502, + "args": { + "External id": 4729937,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360415306.570, "dur": 35554.980, + "args": { + "External id": 4729938,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360415309.149, "dur": 35551.715, + "args": { + "External id": 4729939,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360415313.630, "dur": 7.070, + "args": { + "External id": 4729940,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360415322.363, "dur": 35535.107, + "args": { + "External id": 4729941,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360451017.417, "dur": 8.949, + "args": { + "External id": 4729942,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360451020.145, "dur": 5.630, + "args": { + "External id": 4729943,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360451057.916, "dur": 379.315, + "args": { + "External id": 4729944,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360451098.286, "dur": 333.380, + "args": { + "External id": 4729945,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4696, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360451109.395, "dur": 316.742, + "args": { + "External id": 4729946,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360451461.100, "dur": 2.110, + "args": { + "External id": 4729947,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4698, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360451523.907, "dur": 6.846, + "args": { + "External id": 4729948,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360451572.564, "dur": 1.428, + "args": { + "External id": 4729949,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360451589.037, "dur": 1.140, + "args": { + "External id": 4729950,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360451602.981, "dur": 3.022, + "args": { + "External id": 4729951,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360451616.942, "dur": 0.955, + "args": { + "External id": 4729952,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360451628.142, "dur": 0.773, + "args": { + "External id": 4729953,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360451640.200, "dur": 1.128, + "args": { + "External id": 4729954,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360451652.322, "dur": 3.161, + "args": { + "External id": 4729955,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360451665.664, "dur": 0.805, + "args": { + "External id": 4729956,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360451755.454, "dur": 2795.900, + "args": { + "External id": 4729957,"Record function id": 0, "Ev Idx": 4708 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1712360451774.477, "dur": 1087.084, + "args": { + "External id": 4729958,"Record function id": 0, "Ev Idx": 4709 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1712360451788.881, "dur": 393.448, + "args": { + "External id": 4729959,"Record function id": 0, "Ev Idx": 4710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451865.283, "dur": 4.146, + "args": { + "External id": 4729960,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451872.210, "dur": 0.991, + "args": { + "External id": 4729961,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451876.170, "dur": 1.027, + "args": { + "External id": 4729962,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451878.811, "dur": 0.636, + "args": { + "External id": 4729963,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451881.009, "dur": 2.830, + "args": { + "External id": 4729964,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451885.243, "dur": 0.972, + "args": { + "External id": 4729965,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451888.899, "dur": 1.156, + "args": { + "External id": 4729966,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451891.335, "dur": 0.819, + "args": { + "External id": 4729967,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451893.615, "dur": 1.420, + "args": { + "External id": 4729968,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360451896.477, "dur": 1.060, + "args": { + "External id": 4729969,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360451916.280, "dur": 230.640, + "args": { + "External id": 4729970,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360451931.854, "dur": 209.470, + "args": { + "External id": 4729971,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360451967.368, "dur": 11.895, + "args": { + "External id": 4729972,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360452023.211, "dur": 88.813, + "args": { + "External id": 4729973,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360452025.822, "dur": 85.849, + "args": { + "External id": 4729974,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452032.025, "dur": 7.650, + "args": { + "External id": 4729975,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360452041.394, "dur": 69.244, + "args": { + "External id": 4729976,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4727 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.5", "pid": 1336753, "tid": 1381210, + "ts": 1712360452273.591, "dur": 579.937, + "args": { + "External id": 4729977,"Record function id": 0, "Ev Idx": 4728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1712360452291.362, "dur": 550.387, + "args": { + "External id": 4729978,"Record function id": 0, "Ev Idx": 4729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360452355.165, "dur": 6.938, + "args": { + "External id": 4729979,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360452382.378, "dur": 29.267, + "args": { + "External id": 4729980,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452387.511, "dur": 1.836, + "args": { + "External id": 4729981,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452391.478, "dur": 0.600, + "args": { + "External id": 4729982,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452393.577, "dur": 1.063, + "args": { + "External id": 4729983,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452396.004, "dur": 0.370, + "args": { + "External id": 4729984,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452397.780, "dur": 0.257, + "args": { + "External id": 4729985,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452400.386, "dur": 0.386, + "args": { + "External id": 4729986,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452402.772, "dur": 0.258, + "args": { + "External id": 4729987,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452404.245, "dur": 2.232, + "args": { + "External id": 4729988,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452407.981, "dur": 0.566, + "args": { + "External id": 4729989,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360452424.673, "dur": 29.383, + "args": { + "External id": 4729990,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360452487.199, "dur": 140.000, + "args": { + "External id": 4729991,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360452497.446, "dur": 3.626, + "args": { + "External id": 4729992,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360452506.417, "dur": 9.801, + "args": { + "External id": 4729993,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360452510.413, "dur": 5.377, + "args": { + "External id": 4729994,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452513.911, "dur": 0.671, + "args": { + "External id": 4729995,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360452523.388, "dur": 29.480, + "args": { + "External id": 4729996,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452525.635, "dur": 0.659, + "args": { + "External id": 4729997,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452527.857, "dur": 0.689, + "args": { + "External id": 4729998,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452533.559, "dur": 0.587, + "args": { + "External id": 4729999,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452535.617, "dur": 0.484, + "args": { + "External id": 4730000,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452537.441, "dur": 1.950, + "args": { + "External id": 4730001,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452540.600, "dur": 0.349, + "args": { + "External id": 4730002,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452542.066, "dur": 0.403, + "args": { + "External id": 4730003,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452543.843, "dur": 0.378, + "args": { + "External id": 4730004,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360452545.559, "dur": 0.384, + "args": { + "External id": 4730005,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360452600.586, "dur": 19.643, + "args": { + "External id": 4730006,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360452670.683, "dur": 110.159, + "args": { + "External id": 4730007,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360452696.874, "dur": 80.857, + "args": { + "External id": 4730008,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4759, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360452706.127, "dur": 67.130, + "args": { + "External id": 4730009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360452793.936, "dur": 1.805, + "args": { + "External id": 4730010,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4761, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360452869.164, "dur": 1657.913, + "args": { + "External id": 4730011,"Sequence number": 47018778, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4762 + } + }, + { + "ph": "f", "id": 214, "pid": 1336753, "tid": 1381210, "ts": 1712360452869.164, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360452978.888, "dur": 166.879, + "args": { + "External id": 4730012,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360453196.864, "dur": 39.578, + "args": { + "External id": 4730013,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360453253.768, "dur": 48.906, + "args": { + "External id": 4730014,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360453312.163, "dur": 30.628, + "args": { + "External id": 4730015,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360453349.124, "dur": 43.928, + "args": { + "External id": 4730016,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360453401.756, "dur": 26.894, + "args": { + "External id": 4730017,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360453435.520, "dur": 42.788, + "args": { + "External id": 4730018,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360453501.184, "dur": 22.388, + "args": { + "External id": 4730019,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360453542.206, "dur": 27.297, + "args": { + "External id": 4730020,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360453588.091, "dur": 17.726, + "args": { + "External id": 4730021,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360453621.702, "dur": 13.486, + "args": { + "External id": 4730022,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360453643.265, "dur": 25.871, + "args": { + "External id": 4730023,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360453672.462, "dur": 32.761, + "args": { + "External id": 4730024,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360453737.684, "dur": 171.098, + "args": { + "External id": 4730025,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360453816.314, "dur": 7.003, + "args": { + "External id": 4730026,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360453825.100, "dur": 2.151, + "args": { + "External id": 4730027,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360453943.020, "dur": 23.606, + "args": { + "External id": 4730028,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360453977.172, "dur": 54.444, + "args": { + "External id": 4730029,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360454043.193, "dur": 61.179, + "args": { + "External id": 4730030,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360454112.506, "dur": 41.753, + "args": { + "External id": 4730031,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360454161.426, "dur": 19.923, + "args": { + "External id": 4730032,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360454187.520, "dur": 32.167, + "args": { + "External id": 4730033,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360454225.429, "dur": 36.694, + "args": { + "External id": 4730034,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360454275.737, "dur": 38.909, + "args": { + "External id": 4730035,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360454338.405, "dur": 22.557, + "args": { + "External id": 4730036,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360454384.780, "dur": 23.971, + "args": { + "External id": 4730037,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360454423.454, "dur": 15.902, + "args": { + "External id": 4730038,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360454454.984, "dur": 12.843, + "args": { + "External id": 4730039,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360454480.009, "dur": 18.202, + "args": { + "External id": 4730040,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454572.737, "dur": 13.971, + "args": { + "External id": 4730041,"Record function id": 0, "Ev Idx": 4792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454575.629, "dur": 10.254, + "args": { + "External id": 4730042,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454579.484, "dur": 5.401, + "args": { + "External id": 4730043,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454580.860, "dur": 3.886, + "args": { + "External id": 4730044,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454590.608, "dur": 4.841, + "args": { + "External id": 4730045,"Record function id": 0, "Ev Idx": 4796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454591.795, "dur": 3.257, + "args": { + "External id": 4730046,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454592.917, "dur": 1.611, + "args": { + "External id": 4730047,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454593.602, "dur": 0.812, + "args": { + "External id": 4730048,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454598.688, "dur": 4.074, + "args": { + "External id": 4730049,"Record function id": 0, "Ev Idx": 4800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454599.852, "dur": 2.518, + "args": { + "External id": 4730050,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454600.647, "dur": 1.284, + "args": { + "External id": 4730051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454601.101, "dur": 0.720, + "args": { + "External id": 4730052,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454605.985, "dur": 4.157, + "args": { + "External id": 4730053,"Record function id": 0, "Ev Idx": 4804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454607.034, "dur": 2.723, + "args": { + "External id": 4730054,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454608.080, "dur": 1.067, + "args": { + "External id": 4730055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454608.389, "dur": 0.672, + "args": { + "External id": 4730056,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454613.319, "dur": 5.482, + "args": { + "External id": 4730057,"Record function id": 0, "Ev Idx": 4808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454614.314, "dur": 4.072, + "args": { + "External id": 4730058,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454614.945, "dur": 2.988, + "args": { + "External id": 4730059,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454615.195, "dur": 2.679, + "args": { + "External id": 4730060,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454621.912, "dur": 4.993, + "args": { + "External id": 4730061,"Record function id": 0, "Ev Idx": 4812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454622.891, "dur": 3.606, + "args": { + "External id": 4730062,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454623.583, "dur": 2.498, + "args": { + "External id": 4730063,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454625.116, "dur": 0.872, + "args": { + "External id": 4730064,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454630.230, "dur": 3.837, + "args": { + "External id": 4730065,"Record function id": 0, "Ev Idx": 4816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454631.161, "dur": 2.498, + "args": { + "External id": 4730066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454632.065, "dur": 1.196, + "args": { + "External id": 4730067,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454632.534, "dur": 0.633, + "args": { + "External id": 4730068,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454637.263, "dur": 6.869, + "args": { + "External id": 4730069,"Record function id": 0, "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454638.079, "dur": 5.670, + "args": { + "External id": 4730070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454638.534, "dur": 1.324, + "args": { + "External id": 4730071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454639.113, "dur": 0.651, + "args": { + "External id": 4730072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454647.328, "dur": 3.423, + "args": { + "External id": 4730073,"Record function id": 0, "Ev Idx": 4824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360454648.148, "dur": 2.214, + "args": { + "External id": 4730074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454648.771, "dur": 1.164, + "args": { + "External id": 4730075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360454649.281, "dur": 0.562, + "args": { + "External id": 4730076,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360454654.623, "dur": 37286.334, + "args": { + "External id": 4730077,"Record function id": 0, "Sequence number": 47018777, "Fwd thread id": 1, "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360454656.161, "dur": 37276.495, + "args": { + "External id": 4730078,"Sequence number": 47018777, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4829 + } + }, + { + "ph": "f", "id": 215, "pid": 1336753, "tid": 1381210, "ts": 1712360454656.161, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1712360454685.296, "dur": 39.553, + "args": { + "External id": 4730079,"Record function id": 0, "Ev Idx": 4830 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1712360454732.354, "dur": 63.600, + "args": { + "External id": 4730080,"Record function id": 0, "Ev Idx": 4831 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1712360454802.395, "dur": 37122.707, + "args": { + "External id": 4730081,"Record function id": 0, "Ev Idx": 4832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360454888.294, "dur": 6.350, + "args": { + "External id": 4730082,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360454903.789, "dur": 4.510, + "args": { + "External id": 4730083,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360454922.510, "dur": 36195.632, + "args": { + "External id": 4730084,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360454935.983, "dur": 36173.351, + "args": { + "External id": 4730085,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360455031.527, "dur": 14.414, + "args": { + "External id": 4730086,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360455052.306, "dur": 36008.834, + "args": { + "External id": 4730087,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360455056.479, "dur": 36003.934, + "args": { + "External id": 4730088,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360455060.658, "dur": 22.271, + "args": { + "External id": 4730089,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360455085.636, "dur": 35972.023, + "args": { + "External id": 4730090,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360491205.400, "dur": 8.286, + "args": { + "External id": 4730091,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360491208.302, "dur": 4.992, + "args": { + "External id": 4730092,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360491242.470, "dur": 399.235, + "args": { + "External id": 4730093,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360491269.664, "dur": 367.661, + "args": { + "External id": 4730094,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4845, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360491279.608, "dur": 352.235, + "args": { + "External id": 4730095,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360491663.068, "dur": 2.176, + "args": { + "External id": 4730096,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4847, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360491719.781, "dur": 6.468, + "args": { + "External id": 4730097,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360491771.802, "dur": 1.503, + "args": { + "External id": 4730098,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360491788.061, "dur": 1.331, + "args": { + "External id": 4730099,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360491801.179, "dur": 3.120, + "args": { + "External id": 4730100,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360491818.224, "dur": 1.217, + "args": { + "External id": 4730101,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360491829.812, "dur": 0.837, + "args": { + "External id": 4730102,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360491842.683, "dur": 1.013, + "args": { + "External id": 4730103,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360491854.041, "dur": 3.362, + "args": { + "External id": 4730104,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360491867.306, "dur": 0.684, + "args": { + "External id": 4730105,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360491954.237, "dur": 2680.201, + "args": { + "External id": 4730106,"Record function id": 0, "Ev Idx": 4857 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1712360491972.558, "dur": 1004.030, + "args": { + "External id": 4730107,"Record function id": 0, "Ev Idx": 4858 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1712360492029.274, "dur": 336.376, + "args": { + "External id": 4730108,"Record function id": 0, "Ev Idx": 4859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492132.945, "dur": 5.081, + "args": { + "External id": 4730109,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492141.461, "dur": 1.258, + "args": { + "External id": 4730110,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492146.146, "dur": 0.864, + "args": { + "External id": 4730111,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492148.840, "dur": 1.142, + "args": { + "External id": 4730112,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492151.655, "dur": 1.061, + "args": { + "External id": 4730113,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492154.194, "dur": 2.839, + "args": { + "External id": 4730114,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492159.711, "dur": 0.807, + "args": { + "External id": 4730115,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492161.950, "dur": 0.948, + "args": { + "External id": 4730116,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492164.625, "dur": 1.053, + "args": { + "External id": 4730117,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360492167.240, "dur": 1.330, + "args": { + "External id": 4730118,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360492188.972, "dur": 146.921, + "args": { + "External id": 4730119,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360492205.504, "dur": 125.984, + "args": { + "External id": 4730120,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360492224.212, "dur": 11.616, + "args": { + "External id": 4730121,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360492238.709, "dur": 67.161, + "args": { + "External id": 4730122,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360492241.374, "dur": 64.204, + "args": { + "External id": 4730123,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492245.849, "dur": 6.543, + "args": { + "External id": 4730124,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360492254.049, "dur": 50.992, + "args": { + "External id": 4730125,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4876 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.4", "pid": 1336753, "tid": 1381210, + "ts": 1712360492455.053, "dur": 513.550, + "args": { + "External id": 4730126,"Record function id": 0, "Ev Idx": 4877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1712360492470.751, "dur": 486.550, + "args": { + "External id": 4730127,"Record function id": 0, "Ev Idx": 4878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360492528.718, "dur": 4.827, + "args": { + "External id": 4730128,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360492549.163, "dur": 28.760, + "args": { + "External id": 4730129,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492553.910, "dur": 3.540, + "args": { + "External id": 4730130,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492559.316, "dur": 0.489, + "args": { + "External id": 4730131,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492561.181, "dur": 0.549, + "args": { + "External id": 4730132,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492564.065, "dur": 0.380, + "args": { + "External id": 4730133,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492565.921, "dur": 0.470, + "args": { + "External id": 4730134,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492567.675, "dur": 0.332, + "args": { + "External id": 4730135,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492570.086, "dur": 0.540, + "args": { + "External id": 4730136,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492571.963, "dur": 0.545, + "args": { + "External id": 4730137,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492573.638, "dur": 1.760, + "args": { + "External id": 4730138,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360492587.521, "dur": 29.716, + "args": { + "External id": 4730139,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360492645.027, "dur": 100.229, + "args": { + "External id": 4730140,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360492654.353, "dur": 3.509, + "args": { + "External id": 4730141,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360492663.040, "dur": 9.597, + "args": { + "External id": 4730142,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360492667.121, "dur": 5.116, + "args": { + "External id": 4730143,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492670.684, "dur": 0.447, + "args": { + "External id": 4730144,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360492679.731, "dur": 26.783, + "args": { + "External id": 4730145,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492681.992, "dur": 0.438, + "args": { + "External id": 4730146,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492683.916, "dur": 0.570, + "args": { + "External id": 4730147,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492686.012, "dur": 0.692, + "args": { + "External id": 4730148,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492688.315, "dur": 0.503, + "args": { + "External id": 4730149,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492690.289, "dur": 0.451, + "args": { + "External id": 4730150,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492692.794, "dur": 1.703, + "args": { + "External id": 4730151,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492696.048, "dur": 0.685, + "args": { + "External id": 4730152,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492698.140, "dur": 0.350, + "args": { + "External id": 4730153,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360492699.814, "dur": 0.732, + "args": { + "External id": 4730154,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360492719.492, "dur": 19.029, + "args": { + "External id": 4730155,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360492787.294, "dur": 109.004, + "args": { + "External id": 4730156,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360492813.266, "dur": 79.491, + "args": { + "External id": 4730157,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4908, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360492821.876, "dur": 66.593, + "args": { + "External id": 4730158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360492909.526, "dur": 1.883, + "args": { + "External id": 4730159,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4910, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360493029.436, "dur": 1585.894, + "args": { + "External id": 4730160,"Sequence number": 47018776, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4911 + } + }, + { + "ph": "f", "id": 216, "pid": 1336753, "tid": 1381210, "ts": 1712360493029.436, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360493161.727, "dur": 103.354, + "args": { + "External id": 4730161,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360493311.310, "dur": 39.888, + "args": { + "External id": 4730162,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360493367.420, "dur": 49.159, + "args": { + "External id": 4730163,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360493426.039, "dur": 34.187, + "args": { + "External id": 4730164,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360493466.107, "dur": 43.546, + "args": { + "External id": 4730165,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360493518.220, "dur": 27.887, + "args": { + "External id": 4730166,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360493554.005, "dur": 41.897, + "args": { + "External id": 4730167,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360493617.056, "dur": 20.365, + "args": { + "External id": 4730168,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360493655.917, "dur": 28.261, + "args": { + "External id": 4730169,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360493704.028, "dur": 17.864, + "args": { + "External id": 4730170,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360493737.673, "dur": 13.896, + "args": { + "External id": 4730171,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360493759.992, "dur": 26.266, + "args": { + "External id": 4730172,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360493789.390, "dur": 31.856, + "args": { + "External id": 4730173,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360493847.843, "dur": 212.625, + "args": { + "External id": 4730174,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360493922.021, "dur": 7.146, + "args": { + "External id": 4730175,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360493931.018, "dur": 2.723, + "args": { + "External id": 4730176,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360494116.488, "dur": 25.911, + "args": { + "External id": 4730177,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360494160.689, "dur": 17.063, + "args": { + "External id": 4730178,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360494186.427, "dur": 40.071, + "args": { + "External id": 4730179,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360494235.369, "dur": 34.014, + "args": { + "External id": 4730180,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360494276.448, "dur": 19.077, + "args": { + "External id": 4730181,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360494301.652, "dur": 28.885, + "args": { + "External id": 4730182,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360494335.965, "dur": 19.211, + "args": { + "External id": 4730183,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360494361.248, "dur": 28.525, + "args": { + "External id": 4730184,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360494409.897, "dur": 20.777, + "args": { + "External id": 4730185,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360494450.194, "dur": 36.069, + "args": { + "External id": 4730186,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360494507.641, "dur": 19.929, + "args": { + "External id": 4730187,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360494544.135, "dur": 14.039, + "args": { + "External id": 4730188,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360494571.858, "dur": 15.960, + "args": { + "External id": 4730189,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494659.847, "dur": 14.903, + "args": { + "External id": 4730190,"Record function id": 0, "Ev Idx": 4941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494662.814, "dur": 10.966, + "args": { + "External id": 4730191,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494667.124, "dur": 5.811, + "args": { + "External id": 4730192,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494669.094, "dur": 3.753, + "args": { + "External id": 4730193,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494678.760, "dur": 5.117, + "args": { + "External id": 4730194,"Record function id": 0, "Ev Idx": 4945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494680.238, "dur": 3.202, + "args": { + "External id": 4730195,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494681.278, "dur": 1.635, + "args": { + "External id": 4730196,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494682.049, "dur": 0.784, + "args": { + "External id": 4730197,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494687.286, "dur": 4.188, + "args": { + "External id": 4730198,"Record function id": 0, "Ev Idx": 4949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494688.389, "dur": 2.694, + "args": { + "External id": 4730199,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494689.268, "dur": 1.356, + "args": { + "External id": 4730200,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494689.943, "dur": 0.596, + "args": { + "External id": 4730201,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494694.751, "dur": 7.111, + "args": { + "External id": 4730202,"Record function id": 0, "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494695.877, "dur": 5.571, + "args": { + "External id": 4730203,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494699.815, "dur": 1.211, + "args": { + "External id": 4730204,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494700.301, "dur": 0.659, + "args": { + "External id": 4730205,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494705.086, "dur": 4.902, + "args": { + "External id": 4730206,"Record function id": 0, "Ev Idx": 4957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494706.032, "dur": 3.531, + "args": { + "External id": 4730207,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494706.737, "dur": 2.280, + "args": { + "External id": 4730208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494707.026, "dur": 1.929, + "args": { + "External id": 4730209,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494713.111, "dur": 3.527, + "args": { + "External id": 4730210,"Record function id": 0, "Ev Idx": 4961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494714.289, "dur": 1.953, + "args": { + "External id": 4730211,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494714.742, "dur": 1.060, + "args": { + "External id": 4730212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494715.086, "dur": 0.650, + "args": { + "External id": 4730213,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494719.763, "dur": 4.633, + "args": { + "External id": 4730214,"Record function id": 0, "Ev Idx": 4965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494720.758, "dur": 3.223, + "args": { + "External id": 4730215,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494721.234, "dur": 2.340, + "args": { + "External id": 4730216,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494723.013, "dur": 0.494, + "args": { + "External id": 4730217,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494727.517, "dur": 3.347, + "args": { + "External id": 4730218,"Record function id": 0, "Ev Idx": 4969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494728.491, "dur": 1.974, + "args": { + "External id": 4730219,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494728.988, "dur": 1.058, + "args": { + "External id": 4730220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494729.446, "dur": 0.536, + "args": { + "External id": 4730221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494733.882, "dur": 3.319, + "args": { + "External id": 4730222,"Record function id": 0, "Ev Idx": 4973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360494734.777, "dur": 1.993, + "args": { + "External id": 4730223,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494735.429, "dur": 0.894, + "args": { + "External id": 4730224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360494735.690, "dur": 0.565, + "args": { + "External id": 4730225,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360494741.206, "dur": 37126.237, + "args": { + "External id": 4730226,"Record function id": 0, "Sequence number": 47018775, "Fwd thread id": 1, "Ev Idx": 4977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360494742.821, "dur": 37112.550, + "args": { + "External id": 4730227,"Sequence number": 47018775, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4978 + } + }, + { + "ph": "f", "id": 217, "pid": 1336753, "tid": 1381210, "ts": 1712360494742.821, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1712360494772.543, "dur": 33.963, + "args": { + "External id": 4730228,"Record function id": 0, "Ev Idx": 4979 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1712360494816.383, "dur": 64.213, + "args": { + "External id": 4730229,"Record function id": 0, "Ev Idx": 4980 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1712360494888.028, "dur": 36959.602, + "args": { + "External id": 4730230,"Record function id": 0, "Ev Idx": 4981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360494975.345, "dur": 47.418, + "args": { + "External id": 4730231,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360495035.511, "dur": 4.997, + "args": { + "External id": 4730232,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360495056.545, "dur": 36003.008, + "args": { + "External id": 4730233,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360495085.566, "dur": 35964.658, + "args": { + "External id": 4730234,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360495134.357, "dur": 14.451, + "args": { + "External id": 4730235,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360495155.204, "dur": 35821.748, + "args": { + "External id": 4730236,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360495157.536, "dur": 35818.703, + "args": { + "External id": 4730237,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360495161.574, "dur": 7.285, + "args": { + "External id": 4730238,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360495170.469, "dur": 35802.665, + "args": { + "External id": 4730239,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360531159.342, "dur": 8.860, + "args": { + "External id": 4730240,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360531162.097, "dur": 5.668, + "args": { + "External id": 4730241,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360531195.851, "dur": 372.750, + "args": { + "External id": 4730242,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360531228.061, "dur": 335.357, + "args": { + "External id": 4730243,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4994, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360531238.288, "dur": 319.553, + "args": { + "External id": 4730244,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360531589.436, "dur": 2.089, + "args": { + "External id": 4730245,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4996, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360531647.103, "dur": 6.609, + "args": { + "External id": 4730246,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360531696.207, "dur": 1.480, + "args": { + "External id": 4730247,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360531713.152, "dur": 1.219, + "args": { + "External id": 4730248,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360531726.302, "dur": 2.674, + "args": { + "External id": 4730249,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360531740.155, "dur": 0.864, + "args": { + "External id": 4730250,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360531750.323, "dur": 0.741, + "args": { + "External id": 4730251,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360531762.313, "dur": 1.135, + "args": { + "External id": 4730252,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360531773.840, "dur": 2.986, + "args": { + "External id": 4730253,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360531787.326, "dur": 0.820, + "args": { + "External id": 4730254,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360531881.697, "dur": 2656.280, + "args": { + "External id": 4730255,"Record function id": 0, "Ev Idx": 5006 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1712360531900.598, "dur": 986.494, + "args": { + "External id": 4730256,"Record function id": 0, "Ev Idx": 5007 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1712360531913.098, "dur": 376.509, + "args": { + "External id": 4730257,"Record function id": 0, "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532042.899, "dur": 4.864, + "args": { + "External id": 4730258,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532051.273, "dur": 1.089, + "args": { + "External id": 4730259,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532055.183, "dur": 1.055, + "args": { + "External id": 4730260,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532057.881, "dur": 0.760, + "args": { + "External id": 4730261,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532060.160, "dur": 0.976, + "args": { + "External id": 4730262,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532062.819, "dur": 15.857, + "args": { + "External id": 4730263,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532083.923, "dur": 1.241, + "args": { + "External id": 4730264,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532086.918, "dur": 0.688, + "args": { + "External id": 4730265,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532088.809, "dur": 1.445, + "args": { + "External id": 4730266,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360532091.838, "dur": 1.092, + "args": { + "External id": 4730267,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360532113.340, "dur": 146.187, + "args": { + "External id": 4730268,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360532129.557, "dur": 125.853, + "args": { + "External id": 4730269,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360532147.541, "dur": 12.283, + "args": { + "External id": 4730270,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360532162.953, "dur": 65.528, + "args": { + "External id": 4730271,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360532165.324, "dur": 62.873, + "args": { + "External id": 4730272,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532169.029, "dur": 6.097, + "args": { + "External id": 4730273,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360532176.644, "dur": 50.980, + "args": { + "External id": 4730274,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5025 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.3", "pid": 1336753, "tid": 1381210, + "ts": 1712360532381.383, "dur": 497.641, + "args": { + "External id": 4730275,"Record function id": 0, "Ev Idx": 5026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1712360532397.131, "dur": 470.366, + "args": { + "External id": 4730276,"Record function id": 0, "Ev Idx": 5027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360532454.419, "dur": 4.709, + "args": { + "External id": 4730277,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360532474.226, "dur": 25.453, + "args": { + "External id": 4730278,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532478.882, "dur": 3.560, + "args": { + "External id": 4730279,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532484.021, "dur": 0.643, + "args": { + "External id": 4730280,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532485.673, "dur": 0.303, + "args": { + "External id": 4730281,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532487.738, "dur": 0.244, + "args": { + "External id": 4730282,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532488.763, "dur": 0.234, + "args": { + "External id": 4730283,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532489.889, "dur": 0.373, + "args": { + "External id": 4730284,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532492.105, "dur": 0.419, + "args": { + "External id": 4730285,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532493.611, "dur": 0.266, + "args": { + "External id": 4730286,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532494.962, "dur": 2.244, + "args": { + "External id": 4730287,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360532509.710, "dur": 29.276, + "args": { + "External id": 4730288,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360532566.992, "dur": 92.706, + "args": { + "External id": 4730289,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 5040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360532575.937, "dur": 3.236, + "args": { + "External id": 4730290,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360532583.994, "dur": 9.341, + "args": { + "External id": 4730291,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360532587.849, "dur": 5.074, + "args": { + "External id": 4730292,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 5043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532591.230, "dur": 0.630, + "args": { + "External id": 4730293,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360532599.559, "dur": 23.262, + "args": { + "External id": 4730294,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532602.030, "dur": 0.349, + "args": { + "External id": 4730295,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532604.292, "dur": 0.505, + "args": { + "External id": 4730296,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532606.102, "dur": 0.587, + "args": { + "External id": 4730297,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532607.858, "dur": 0.261, + "args": { + "External id": 4730298,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532608.959, "dur": 0.365, + "args": { + "External id": 4730299,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532610.492, "dur": 1.647, + "args": { + "External id": 4730300,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532613.298, "dur": 0.304, + "args": { + "External id": 4730301,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532614.458, "dur": 0.264, + "args": { + "External id": 4730302,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360532615.701, "dur": 0.311, + "args": { + "External id": 4730303,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360532634.283, "dur": 18.486, + "args": { + "External id": 4730304,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360532699.568, "dur": 106.076, + "args": { + "External id": 4730305,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 5056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360532724.078, "dur": 78.311, + "args": { + "External id": 4730306,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5057, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360532732.463, "dur": 66.043, + "args": { + "External id": 4730307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 5058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360532819.166, "dur": 1.824, + "args": { + "External id": 4730308,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5059, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360532894.971, "dur": 1625.269, + "args": { + "External id": 4730309,"Sequence number": 47018774, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5060 + } + }, + { + "ph": "f", "id": 218, "pid": 1336753, "tid": 1381210, "ts": 1712360532894.971, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360533046.836, "dur": 121.660, + "args": { + "External id": 4730310,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360533215.025, "dur": 37.808, + "args": { + "External id": 4730311,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360533270.392, "dur": 47.251, + "args": { + "External id": 4730312,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360533327.083, "dur": 31.993, + "args": { + "External id": 4730313,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360533365.794, "dur": 46.194, + "args": { + "External id": 4730314,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360533420.305, "dur": 27.084, + "args": { + "External id": 4730315,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360533454.633, "dur": 42.405, + "args": { + "External id": 4730316,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360533519.535, "dur": 27.127, + "args": { + "External id": 4730317,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360533564.969, "dur": 29.259, + "args": { + "External id": 4730318,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360533612.404, "dur": 16.689, + "args": { + "External id": 4730319,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360533646.207, "dur": 13.076, + "args": { + "External id": 4730320,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360533669.087, "dur": 25.531, + "args": { + "External id": 4730321,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360533700.871, "dur": 31.285, + "args": { + "External id": 4730322,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360533760.840, "dur": 167.601, + "args": { + "External id": 4730323,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360533838.007, "dur": 5.429, + "args": { + "External id": 4730324,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360533845.174, "dur": 4.619, + "args": { + "External id": 4730325,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360533960.616, "dur": 22.125, + "args": { + "External id": 4730326,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360534035.204, "dur": 18.300, + "args": { + "External id": 4730327,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360534063.500, "dur": 60.298, + "args": { + "External id": 4730328,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360534131.662, "dur": 36.713, + "args": { + "External id": 4730329,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360534175.153, "dur": 19.066, + "args": { + "External id": 4730330,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360534200.158, "dur": 29.667, + "args": { + "External id": 4730331,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360534234.508, "dur": 18.231, + "args": { + "External id": 4730332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360534259.024, "dur": 30.849, + "args": { + "External id": 4730333,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360534310.193, "dur": 19.943, + "args": { + "External id": 4730334,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360534348.487, "dur": 39.195, + "args": { + "External id": 4730335,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360534413.773, "dur": 17.130, + "args": { + "External id": 4730336,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360534448.197, "dur": 14.013, + "args": { + "External id": 4730337,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360534474.978, "dur": 16.259, + "args": { + "External id": 4730338,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534586.770, "dur": 16.285, + "args": { + "External id": 4730339,"Record function id": 0, "Ev Idx": 5090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534590.452, "dur": 11.429, + "args": { + "External id": 4730340,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534594.809, "dur": 5.822, + "args": { + "External id": 4730341,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534596.376, "dur": 4.042, + "args": { + "External id": 4730342,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534606.925, "dur": 4.599, + "args": { + "External id": 4730343,"Record function id": 0, "Ev Idx": 5094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534608.337, "dur": 2.787, + "args": { + "External id": 4730344,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534609.060, "dur": 1.622, + "args": { + "External id": 4730345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534609.542, "dur": 1.041, + "args": { + "External id": 4730346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534614.871, "dur": 3.768, + "args": { + "External id": 4730347,"Record function id": 0, "Ev Idx": 5098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534616.040, "dur": 2.206, + "args": { + "External id": 4730348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534616.518, "dur": 1.290, + "args": { + "External id": 4730349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534617.081, "dur": 0.637, + "args": { + "External id": 4730350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534621.929, "dur": 3.935, + "args": { + "External id": 4730351,"Record function id": 0, "Ev Idx": 5102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534623.054, "dur": 2.384, + "args": { + "External id": 4730352,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534623.611, "dur": 1.437, + "args": { + "External id": 4730353,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534624.119, "dur": 0.863, + "args": { + "External id": 4730354,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534629.021, "dur": 5.224, + "args": { + "External id": 4730355,"Record function id": 0, "Ev Idx": 5106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534630.139, "dur": 3.712, + "args": { + "External id": 4730356,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534630.755, "dur": 2.496, + "args": { + "External id": 4730357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534631.132, "dur": 2.039, + "args": { + "External id": 4730358,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534637.524, "dur": 5.019, + "args": { + "External id": 4730359,"Record function id": 0, "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534638.645, "dur": 3.476, + "args": { + "External id": 4730360,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534639.288, "dur": 2.371, + "args": { + "External id": 4730361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534640.880, "dur": 0.711, + "args": { + "External id": 4730362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534645.804, "dur": 3.426, + "args": { + "External id": 4730363,"Record function id": 0, "Ev Idx": 5114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534646.792, "dur": 2.038, + "args": { + "External id": 4730364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534647.323, "dur": 1.098, + "args": { + "External id": 4730365,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534647.738, "dur": 0.617, + "args": { + "External id": 4730366,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534652.448, "dur": 83.390, + "args": { + "External id": 4730367,"Record function id": 0, "Ev Idx": 5118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534653.514, "dur": 81.777, + "args": { + "External id": 4730368,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534732.840, "dur": 1.752, + "args": { + "External id": 4730369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534733.723, "dur": 0.797, + "args": { + "External id": 4730370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534739.445, "dur": 5.440, + "args": { + "External id": 4730371,"Record function id": 0, "Ev Idx": 5122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360534740.615, "dur": 3.852, + "args": { + "External id": 4730372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534741.231, "dur": 2.728, + "args": { + "External id": 4730373,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360534743.289, "dur": 0.565, + "args": { + "External id": 4730374,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360534749.005, "dur": 37106.042, + "args": { + "External id": 4730375,"Record function id": 0, "Sequence number": 47018773, "Fwd thread id": 1, "Ev Idx": 5126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360534750.929, "dur": 37095.820, + "args": { + "External id": 4730376,"Sequence number": 47018773, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5127 + } + }, + { + "ph": "f", "id": 219, "pid": 1336753, "tid": 1381210, "ts": 1712360534750.929, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1712360534780.547, "dur": 38.037, + "args": { + "External id": 4730377,"Record function id": 0, "Ev Idx": 5128 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1712360534826.014, "dur": 64.233, + "args": { + "External id": 4730378,"Record function id": 0, "Ev Idx": 5129 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1712360534895.874, "dur": 36943.698, + "args": { + "External id": 4730379,"Record function id": 0, "Ev Idx": 5130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360535019.578, "dur": 9.887, + "args": { + "External id": 4730380,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360535042.358, "dur": 5.236, + "args": { + "External id": 4730381,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360535063.101, "dur": 36027.730, + "args": { + "External id": 4730382,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360535091.930, "dur": 35989.291, + "args": { + "External id": 4730383,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360535138.670, "dur": 18.264, + "args": { + "External id": 4730384,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360535164.797, "dur": 35868.429, + "args": { + "External id": 4730385,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360535167.224, "dur": 35865.105, + "args": { + "External id": 4730386,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360535171.120, "dur": 7.344, + "args": { + "External id": 4730387,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360535180.237, "dur": 35848.753, + "args": { + "External id": 4730388,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360571180.974, "dur": 9.306, + "args": { + "External id": 4730389,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360571183.732, "dur": 6.166, + "args": { + "External id": 4730390,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360571220.499, "dur": 343.172, + "args": { + "External id": 4730391,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360571247.696, "dur": 311.404, + "args": { + "External id": 4730392,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5143, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360571258.000, "dur": 295.793, + "args": { + "External id": 4730393,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360571582.091, "dur": 2.092, + "args": { + "External id": 4730394,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5145, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360571638.690, "dur": 6.145, + "args": { + "External id": 4730395,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360571688.000, "dur": 1.335, + "args": { + "External id": 4730396,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360571704.046, "dur": 1.343, + "args": { + "External id": 4730397,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360571716.543, "dur": 2.451, + "args": { + "External id": 4730398,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360571730.451, "dur": 0.743, + "args": { + "External id": 4730399,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360571740.777, "dur": 0.982, + "args": { + "External id": 4730400,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360571752.699, "dur": 1.022, + "args": { + "External id": 4730401,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360571764.136, "dur": 3.036, + "args": { + "External id": 4730402,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360571779.995, "dur": 0.960, + "args": { + "External id": 4730403,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360571868.984, "dur": 2694.166, + "args": { + "External id": 4730404,"Record function id": 0, "Ev Idx": 5155 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1712360571888.503, "dur": 1027.265, + "args": { + "External id": 4730405,"Record function id": 0, "Ev Idx": 5156 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1712360571902.267, "dur": 398.044, + "args": { + "External id": 4730406,"Record function id": 0, "Ev Idx": 5157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360571979.839, "dur": 46.982, + "args": { + "External id": 4730407,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360572032.611, "dur": 1.069, + "args": { + "External id": 4730408,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360572036.538, "dur": 0.798, + "args": { + "External id": 4730409,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360572039.099, "dur": 0.763, + "args": { + "External id": 4730410,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360572041.346, "dur": 0.720, + "args": { + "External id": 4730411,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360572043.373, "dur": 2.330, + "args": { + "External id": 4730412,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360572048.647, "dur": 1.198, + "args": { + "External id": 4730413,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360572051.226, "dur": 1.104, + "args": { + "External id": 4730414,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360572053.762, "dur": 1.166, + "args": { + "External id": 4730415,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360572056.057, "dur": 1.133, + "args": { + "External id": 4730416,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360572092.499, "dur": 172.380, + "args": { + "External id": 4730417,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360572108.945, "dur": 151.077, + "args": { + "External id": 4730418,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360572146.056, "dur": 13.057, + "args": { + "External id": 4730419,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360572162.088, "dur": 70.188, + "args": { + "External id": 4730420,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360572164.639, "dur": 67.358, + "args": { + "External id": 4730421,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572168.236, "dur": 6.196, + "args": { + "External id": 4730422,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360572176.001, "dur": 55.211, + "args": { + "External id": 4730423,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5174 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.2", "pid": 1336753, "tid": 1381210, + "ts": 1712360572401.759, "dur": 506.216, + "args": { + "External id": 4730424,"Record function id": 0, "Ev Idx": 5175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1712360572419.426, "dur": 476.399, + "args": { + "External id": 4730425,"Record function id": 0, "Ev Idx": 5176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360572480.947, "dur": 5.055, + "args": { + "External id": 4730426,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360572501.461, "dur": 24.713, + "args": { + "External id": 4730427,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572505.867, "dur": 3.087, + "args": { + "External id": 4730428,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572510.573, "dur": 0.539, + "args": { + "External id": 4730429,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572511.866, "dur": 0.406, + "args": { + "External id": 4730430,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572513.904, "dur": 0.406, + "args": { + "External id": 4730431,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572515.213, "dur": 0.307, + "args": { + "External id": 4730432,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572516.398, "dur": 1.161, + "args": { + "External id": 4730433,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572518.524, "dur": 0.419, + "args": { + "External id": 4730434,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572519.771, "dur": 0.377, + "args": { + "External id": 4730435,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572521.529, "dur": 1.663, + "args": { + "External id": 4730436,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360572535.348, "dur": 28.297, + "args": { + "External id": 4730437,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360572592.138, "dur": 90.777, + "args": { + "External id": 4730438,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 5189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360572601.407, "dur": 2.817, + "args": { + "External id": 4730439,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360572609.497, "dur": 9.437, + "args": { + "External id": 4730440,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360572613.338, "dur": 5.200, + "args": { + "External id": 4730441,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 5192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572616.442, "dur": 0.627, + "args": { + "External id": 4730442,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360572625.753, "dur": 20.880, + "args": { + "External id": 4730443,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572627.321, "dur": 0.284, + "args": { + "External id": 4730444,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572628.764, "dur": 0.510, + "args": { + "External id": 4730445,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572630.553, "dur": 0.413, + "args": { + "External id": 4730446,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572631.865, "dur": 0.308, + "args": { + "External id": 4730447,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572633.279, "dur": 0.359, + "args": { + "External id": 4730448,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572634.943, "dur": 1.531, + "args": { + "External id": 4730449,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572637.235, "dur": 0.365, + "args": { + "External id": 4730450,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572638.342, "dur": 0.544, + "args": { + "External id": 4730451,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360572639.842, "dur": 0.398, + "args": { + "External id": 4730452,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360572657.299, "dur": 18.628, + "args": { + "External id": 4730453,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360572723.495, "dur": 108.163, + "args": { + "External id": 4730454,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 5205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360572747.029, "dur": 81.569, + "args": { + "External id": 4730455,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5206, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360572755.602, "dur": 67.988, + "args": { + "External id": 4730456,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 5207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360572845.830, "dur": 1.687, + "args": { + "External id": 4730457,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5208, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360572925.713, "dur": 1614.696, + "args": { + "External id": 4730458,"Sequence number": 47018772, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5209 + } + }, + { + "ph": "f", "id": 220, "pid": 1336753, "tid": 1381210, "ts": 1712360572925.713, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360573088.712, "dur": 104.434, + "args": { + "External id": 4730459,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360573236.963, "dur": 37.825, + "args": { + "External id": 4730460,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360573291.029, "dur": 45.547, + "args": { + "External id": 4730461,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360573345.826, "dur": 31.650, + "args": { + "External id": 4730462,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360573383.608, "dur": 49.173, + "args": { + "External id": 4730463,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360573440.881, "dur": 29.563, + "args": { + "External id": 4730464,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360573477.543, "dur": 42.339, + "args": { + "External id": 4730465,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360573545.241, "dur": 22.453, + "args": { + "External id": 4730466,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360573589.981, "dur": 27.133, + "args": { + "External id": 4730467,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360573635.532, "dur": 21.050, + "args": { + "External id": 4730468,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360573669.887, "dur": 13.374, + "args": { + "External id": 4730469,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360573691.654, "dur": 29.941, + "args": { + "External id": 4730470,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360573724.679, "dur": 31.044, + "args": { + "External id": 4730471,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360573785.171, "dur": 166.714, + "args": { + "External id": 4730472,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360573864.732, "dur": 5.872, + "args": { + "External id": 4730473,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360573872.147, "dur": 2.190, + "args": { + "External id": 4730474,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360574026.589, "dur": 28.891, + "args": { + "External id": 4730475,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360574084.853, "dur": 17.817, + "args": { + "External id": 4730476,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360574113.800, "dur": 41.401, + "args": { + "External id": 4730477,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360574161.394, "dur": 36.112, + "args": { + "External id": 4730478,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360574203.475, "dur": 19.388, + "args": { + "External id": 4730479,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360574226.465, "dur": 29.954, + "args": { + "External id": 4730480,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360574262.908, "dur": 18.796, + "args": { + "External id": 4730481,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360574288.951, "dur": 28.949, + "args": { + "External id": 4730482,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360574337.058, "dur": 20.505, + "args": { + "External id": 4730483,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360574388.828, "dur": 29.113, + "args": { + "External id": 4730484,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360574436.115, "dur": 16.525, + "args": { + "External id": 4730485,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360574468.919, "dur": 12.782, + "args": { + "External id": 4730486,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360574493.911, "dur": 19.103, + "args": { + "External id": 4730487,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574585.405, "dur": 16.447, + "args": { + "External id": 4730488,"Record function id": 0, "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574588.669, "dur": 12.226, + "args": { + "External id": 4730489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574592.639, "dur": 7.340, + "args": { + "External id": 4730490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574594.172, "dur": 5.673, + "args": { + "External id": 4730491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574605.727, "dur": 5.470, + "args": { + "External id": 4730492,"Record function id": 0, "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574607.096, "dur": 3.671, + "args": { + "External id": 4730493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574607.924, "dur": 2.003, + "args": { + "External id": 4730494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574608.862, "dur": 0.978, + "args": { + "External id": 4730495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574614.461, "dur": 8.196, + "args": { + "External id": 4730496,"Record function id": 0, "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574619.014, "dur": 3.228, + "args": { + "External id": 4730497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574619.934, "dur": 1.847, + "args": { + "External id": 4730498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574620.646, "dur": 1.072, + "args": { + "External id": 4730499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574625.917, "dur": 4.298, + "args": { + "External id": 4730500,"Record function id": 0, "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574627.072, "dur": 2.714, + "args": { + "External id": 4730501,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574627.765, "dur": 1.459, + "args": { + "External id": 4730502,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574628.554, "dur": 0.607, + "args": { + "External id": 4730503,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574633.374, "dur": 3.168, + "args": { + "External id": 4730504,"Record function id": 0, "Ev Idx": 5255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574634.304, "dur": 1.833, + "args": { + "External id": 4730505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574634.779, "dur": 0.917, + "args": { + "External id": 4730506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574635.074, "dur": 0.556, + "args": { + "External id": 4730507,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574639.915, "dur": 3.712, + "args": { + "External id": 4730508,"Record function id": 0, "Ev Idx": 5259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574640.823, "dur": 2.390, + "args": { + "External id": 4730509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574641.430, "dur": 1.197, + "args": { + "External id": 4730510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574641.893, "dur": 0.632, + "args": { + "External id": 4730511,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574647.345, "dur": 3.713, + "args": { + "External id": 4730512,"Record function id": 0, "Ev Idx": 5263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574648.324, "dur": 2.312, + "args": { + "External id": 4730513,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574649.190, "dur": 1.010, + "args": { + "External id": 4730514,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574649.497, "dur": 0.621, + "args": { + "External id": 4730515,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574654.155, "dur": 9.040, + "args": { + "External id": 4730516,"Record function id": 0, "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574655.329, "dur": 7.438, + "args": { + "External id": 4730517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574659.252, "dur": 3.106, + "args": { + "External id": 4730518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574659.814, "dur": 2.452, + "args": { + "External id": 4730519,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574666.471, "dur": 5.023, + "args": { + "External id": 4730520,"Record function id": 0, "Ev Idx": 5271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360574667.633, "dur": 3.442, + "args": { + "External id": 4730521,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574668.493, "dur": 2.122, + "args": { + "External id": 4730522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360574669.685, "dur": 0.804, + "args": { + "External id": 4730523,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360574678.238, "dur": 37776.692, + "args": { + "External id": 4730524,"Record function id": 0, "Sequence number": 47018771, "Fwd thread id": 1, "Ev Idx": 5275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360574679.485, "dur": 37766.828, + "args": { + "External id": 4730525,"Sequence number": 47018771, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5276 + } + }, + { + "ph": "f", "id": 221, "pid": 1336753, "tid": 1381210, "ts": 1712360574679.485, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1712360574707.354, "dur": 36.799, + "args": { + "External id": 4730526,"Record function id": 0, "Ev Idx": 5277 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1712360574751.949, "dur": 63.760, + "args": { + "External id": 4730527,"Record function id": 0, "Ev Idx": 5278 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1712360574821.684, "dur": 37617.099, + "args": { + "External id": 4730528,"Record function id": 0, "Ev Idx": 5279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360574906.878, "dur": 6.520, + "args": { + "External id": 4730529,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360574922.765, "dur": 4.614, + "args": { + "External id": 4730530,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360574941.323, "dur": 36612.933, + "args": { + "External id": 4730531,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360574954.151, "dur": 36590.975, + "args": { + "External id": 4730532,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360575041.449, "dur": 13.915, + "args": { + "External id": 4730533,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360575061.546, "dur": 36445.965, + "args": { + "External id": 4730534,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360575064.131, "dur": 36442.705, + "args": { + "External id": 4730535,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360575086.360, "dur": 6.849, + "args": { + "External id": 4730536,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360575095.002, "dur": 36408.450, + "args": { + "External id": 4730537,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360611641.958, "dur": 8.892, + "args": { + "External id": 4730538,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360611644.864, "dur": 5.654, + "args": { + "External id": 4730539,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360611679.153, "dur": 466.077, + "args": { + "External id": 4730540,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360611706.330, "dur": 432.492, + "args": { + "External id": 4730541,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5292, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360611716.654, "dur": 415.684, + "args": { + "External id": 4730542,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360612165.401, "dur": 2.708, + "args": { + "External id": 4730543,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5294, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612231.609, "dur": 6.708, + "args": { + "External id": 4730544,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612281.034, "dur": 1.565, + "args": { + "External id": 4730545,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612298.558, "dur": 3.010, + "args": { + "External id": 4730546,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612313.341, "dur": 1.347, + "args": { + "External id": 4730547,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612325.692, "dur": 1.627, + "args": { + "External id": 4730548,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612337.338, "dur": 1.322, + "args": { + "External id": 4730549,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612348.846, "dur": 2.855, + "args": { + "External id": 4730550,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612365.461, "dur": 1.452, + "args": { + "External id": 4730551,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612376.900, "dur": 0.748, + "args": { + "External id": 4730552,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360612468.625, "dur": 2698.086, + "args": { + "External id": 4730553,"Record function id": 0, "Ev Idx": 5304 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1712360612487.494, "dur": 1054.134, + "args": { + "External id": 4730554,"Record function id": 0, "Ev Idx": 5305 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1712360612501.753, "dur": 301.270, + "args": { + "External id": 4730555,"Record function id": 0, "Ev Idx": 5306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612580.044, "dur": 4.214, + "args": { + "External id": 4730556,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612587.261, "dur": 1.162, + "args": { + "External id": 4730557,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612589.939, "dur": 0.998, + "args": { + "External id": 4730558,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612592.637, "dur": 3.047, + "args": { + "External id": 4730559,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612597.199, "dur": 1.218, + "args": { + "External id": 4730560,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612599.712, "dur": 0.852, + "args": { + "External id": 4730561,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612603.635, "dur": 1.278, + "args": { + "External id": 4730562,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612606.392, "dur": 0.998, + "args": { + "External id": 4730563,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612608.883, "dur": 0.925, + "args": { + "External id": 4730564,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360612610.952, "dur": 1.363, + "args": { + "External id": 4730565,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360612630.742, "dur": 145.557, + "args": { + "External id": 4730566,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360612646.557, "dur": 125.730, + "args": { + "External id": 4730567,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360612663.176, "dur": 12.598, + "args": { + "External id": 4730568,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360612679.026, "dur": 67.382, + "args": { + "External id": 4730569,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360612681.694, "dur": 64.324, + "args": { + "External id": 4730570,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360612686.010, "dur": 7.490, + "args": { + "External id": 4730571,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360612695.283, "dur": 50.023, + "args": { + "External id": 4730572,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5323 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.1", "pid": 1336753, "tid": 1381210, + "ts": 1712360612895.319, "dur": 638.620, + "args": { + "External id": 4730573,"Record function id": 0, "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1712360612911.043, "dur": 610.195, + "args": { + "External id": 4730574,"Record function id": 0, "Ev Idx": 5325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360612968.573, "dur": 3.960, + "args": { + "External id": 4730575,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360613086.190, "dur": 28.933, + "args": { + "External id": 4730576,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613092.750, "dur": 1.870, + "args": { + "External id": 4730577,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613096.904, "dur": 0.717, + "args": { + "External id": 4730578,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613098.656, "dur": 0.456, + "args": { + "External id": 4730579,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613100.667, "dur": 0.496, + "args": { + "External id": 4730580,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613102.649, "dur": 0.497, + "args": { + "External id": 4730581,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613104.152, "dur": 0.477, + "args": { + "External id": 4730582,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613106.125, "dur": 2.414, + "args": { + "External id": 4730583,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613109.992, "dur": 0.334, + "args": { + "External id": 4730584,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613111.408, "dur": 0.457, + "args": { + "External id": 4730585,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360613125.581, "dur": 35.409, + "args": { + "External id": 4730586,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360613194.480, "dur": 102.348, + "args": { + "External id": 4730587,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 5338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360613205.929, "dur": 4.668, + "args": { + "External id": 4730588,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360613215.933, "dur": 10.592, + "args": { + "External id": 4730589,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360613220.237, "dur": 5.902, + "args": { + "External id": 4730590,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 5341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613224.451, "dur": 0.466, + "args": { + "External id": 4730591,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360613233.541, "dur": 26.484, + "args": { + "External id": 4730592,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613235.617, "dur": 0.549, + "args": { + "External id": 4730593,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613237.902, "dur": 0.380, + "args": { + "External id": 4730594,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613239.997, "dur": 0.834, + "args": { + "External id": 4730595,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613242.223, "dur": 1.455, + "args": { + "External id": 4730596,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613244.783, "dur": 0.599, + "args": { + "External id": 4730597,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613246.561, "dur": 0.489, + "args": { + "External id": 4730598,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613250.305, "dur": 0.310, + "args": { + "External id": 4730599,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613251.826, "dur": 0.466, + "args": { + "External id": 4730600,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360613253.938, "dur": 0.563, + "args": { + "External id": 4730601,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360613270.999, "dur": 18.347, + "args": { + "External id": 4730602,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360613343.806, "dur": 110.610, + "args": { + "External id": 4730603,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 5354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360613367.883, "dur": 83.501, + "args": { + "External id": 4730604,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5355, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360613377.134, "dur": 70.071, + "args": { + "External id": 4730605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 5356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360613467.874, "dur": 1.777, + "args": { + "External id": 4730606,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5357, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360613548.990, "dur": 1594.794, + "args": { + "External id": 4730607,"Sequence number": 47018770, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5358 + } + }, + { + "ph": "f", "id": 222, "pid": 1336753, "tid": 1381210, "ts": 1712360613548.990, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360613660.439, "dur": 97.874, + "args": { + "External id": 4730608,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360613797.351, "dur": 35.754, + "args": { + "External id": 4730609,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360613849.079, "dur": 46.646, + "args": { + "External id": 4730610,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360613904.539, "dur": 30.785, + "args": { + "External id": 4730611,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360613941.435, "dur": 89.331, + "args": { + "External id": 4730612,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614043.826, "dur": 45.360, + "args": { + "External id": 4730613,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614098.880, "dur": 46.054, + "args": { + "External id": 4730614,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360614171.982, "dur": 23.790, + "args": { + "External id": 4730615,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360614213.852, "dur": 28.134, + "args": { + "External id": 4730616,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360614261.968, "dur": 18.228, + "args": { + "External id": 4730617,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360614293.601, "dur": 13.680, + "args": { + "External id": 4730618,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614317.728, "dur": 28.639, + "args": { + "External id": 4730619,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614349.491, "dur": 31.528, + "args": { + "External id": 4730620,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360614408.375, "dur": 161.778, + "args": { + "External id": 4730621,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360614481.260, "dur": 5.680, + "args": { + "External id": 4730622,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360614488.693, "dur": 2.107, + "args": { + "External id": 4730623,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360614602.451, "dur": 22.477, + "args": { + "External id": 4730624,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360614635.061, "dur": 17.141, + "args": { + "External id": 4730625,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614661.344, "dur": 30.673, + "args": { + "External id": 4730626,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614698.356, "dur": 36.356, + "args": { + "External id": 4730627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614740.954, "dur": 19.992, + "args": { + "External id": 4730628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614766.024, "dur": 29.624, + "args": { + "External id": 4730629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614802.994, "dur": 19.771, + "args": { + "External id": 4730630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360614830.400, "dur": 29.953, + "args": { + "External id": 4730631,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360614875.398, "dur": 19.889, + "args": { + "External id": 4730632,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360614910.324, "dur": 24.125, + "args": { + "External id": 4730633,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360614947.223, "dur": 14.874, + "args": { + "External id": 4730634,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360614977.920, "dur": 75.249, + "args": { + "External id": 4730635,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360615093.583, "dur": 19.333, + "args": { + "External id": 4730636,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615188.625, "dur": 14.514, + "args": { + "External id": 4730637,"Record function id": 0, "Ev Idx": 5388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615191.631, "dur": 10.505, + "args": { + "External id": 4730638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615195.589, "dur": 5.629, + "args": { + "External id": 4730639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615197.060, "dur": 4.017, + "args": { + "External id": 4730640,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615210.209, "dur": 6.479, + "args": { + "External id": 4730641,"Record function id": 0, "Ev Idx": 5392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615211.395, "dur": 4.839, + "args": { + "External id": 4730642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615212.283, "dur": 3.418, + "args": { + "External id": 4730643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615212.929, "dur": 2.709, + "args": { + "External id": 4730644,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615220.121, "dur": 4.188, + "args": { + "External id": 4730645,"Record function id": 0, "Ev Idx": 5396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615221.176, "dur": 2.738, + "args": { + "External id": 4730646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615221.863, "dur": 1.563, + "args": { + "External id": 4730647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615222.178, "dur": 1.186, + "args": { + "External id": 4730648,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615227.597, "dur": 3.868, + "args": { + "External id": 4730649,"Record function id": 0, "Ev Idx": 5400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615228.693, "dur": 2.367, + "args": { + "External id": 4730650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615229.267, "dur": 1.345, + "args": { + "External id": 4730651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615229.742, "dur": 0.803, + "args": { + "External id": 4730652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615234.640, "dur": 3.602, + "args": { + "External id": 4730653,"Record function id": 0, "Ev Idx": 5404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615235.852, "dur": 1.976, + "args": { + "External id": 4730654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615236.408, "dur": 0.998, + "args": { + "External id": 4730655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615236.804, "dur": 0.536, + "args": { + "External id": 4730656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615241.426, "dur": 4.400, + "args": { + "External id": 4730657,"Record function id": 0, "Ev Idx": 5408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615242.539, "dur": 2.870, + "args": { + "External id": 4730658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615243.665, "dur": 1.321, + "args": { + "External id": 4730659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615244.134, "dur": 0.752, + "args": { + "External id": 4730660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615249.437, "dur": 4.064, + "args": { + "External id": 4730661,"Record function id": 0, "Ev Idx": 5412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615250.568, "dur": 2.517, + "args": { + "External id": 4730662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615251.396, "dur": 1.255, + "args": { + "External id": 4730663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615252.061, "dur": 0.486, + "args": { + "External id": 4730664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615256.645, "dur": 3.787, + "args": { + "External id": 4730665,"Record function id": 0, "Ev Idx": 5416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615257.627, "dur": 2.356, + "args": { + "External id": 4730666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615258.364, "dur": 1.218, + "args": { + "External id": 4730667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615258.647, "dur": 0.835, + "args": { + "External id": 4730668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615263.498, "dur": 6.405, + "args": { + "External id": 4730669,"Record function id": 0, "Ev Idx": 5420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360615264.633, "dur": 4.850, + "args": { + "External id": 4730670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615265.312, "dur": 3.723, + "args": { + "External id": 4730671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360615265.918, "dur": 2.975, + "args": { + "External id": 4730672,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360615273.684, "dur": 36687.179, + "args": { + "External id": 4730673,"Record function id": 0, "Sequence number": 47018769, "Fwd thread id": 1, "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360615275.029, "dur": 36677.837, + "args": { + "External id": 4730674,"Sequence number": 47018769, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5425 + } + }, + { + "ph": "f", "id": 223, "pid": 1336753, "tid": 1381210, "ts": 1712360615275.029, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1712360615301.470, "dur": 35.566, + "args": { + "External id": 4730675,"Record function id": 0, "Ev Idx": 5426 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1712360615344.616, "dur": 64.835, + "args": { + "External id": 4730676,"Record function id": 0, "Ev Idx": 5427 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1712360615415.325, "dur": 36530.614, + "args": { + "External id": 4730677,"Record function id": 0, "Ev Idx": 5428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360615499.880, "dur": 7.542, + "args": { + "External id": 4730678,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360615515.941, "dur": 4.753, + "args": { + "External id": 4730679,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360615534.549, "dur": 35643.456, + "args": { + "External id": 4730680,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360615547.551, "dur": 35621.852, + "args": { + "External id": 4730681,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360615607.461, "dur": 13.220, + "args": { + "External id": 4730682,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360615627.925, "dur": 35504.811, + "args": { + "External id": 4730683,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360615630.441, "dur": 35501.518, + "args": { + "External id": 4730684,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360615635.107, "dur": 5.254, + "args": { + "External id": 4730685,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360615642.102, "dur": 35486.517, + "args": { + "External id": 4730686,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360651265.815, "dur": 10.187, + "args": { + "External id": 4730687,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360651268.408, "dur": 7.235, + "args": { + "External id": 4730688,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360651303.674, "dur": 370.825, + "args": { + "External id": 4730689,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360651331.667, "dur": 337.508, + "args": { + "External id": 4730690,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5441, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360651342.084, "dur": 321.519, + "args": { + "External id": 4730691,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360651692.926, "dur": 2.374, + "args": { + "External id": 4730692,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5443, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360651751.902, "dur": 6.659, + "args": { + "External id": 4730693,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360651801.705, "dur": 1.639, + "args": { + "External id": 4730694,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360651820.637, "dur": 0.953, + "args": { + "External id": 4730695,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360651832.126, "dur": 1.031, + "args": { + "External id": 4730696,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360651843.335, "dur": 1.113, + "args": { + "External id": 4730697,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360651854.123, "dur": 0.795, + "args": { + "External id": 4730698,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360651865.900, "dur": 0.809, + "args": { + "External id": 4730699,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360651877.530, "dur": 1.242, + "args": { + "External id": 4730700,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360651888.282, "dur": 0.870, + "args": { + "External id": 4730701,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360651974.133, "dur": 2627.134, + "args": { + "External id": 4730702,"Record function id": 0, "Ev Idx": 5453 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1712360652032.722, "dur": 940.288, + "args": { + "External id": 4730703,"Record function id": 0, "Ev Idx": 5454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1712360652046.097, "dur": 335.847, + "args": { + "External id": 4730704,"Record function id": 0, "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652150.005, "dur": 4.890, + "args": { + "External id": 4730705,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652158.055, "dur": 0.958, + "args": { + "External id": 4730706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652160.711, "dur": 0.985, + "args": { + "External id": 4730707,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652163.274, "dur": 2.758, + "args": { + "External id": 4730708,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652168.268, "dur": 0.908, + "args": { + "External id": 4730709,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652170.650, "dur": 0.723, + "args": { + "External id": 4730710,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652173.494, "dur": 0.977, + "args": { + "External id": 4730711,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652175.764, "dur": 1.033, + "args": { + "External id": 4730712,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652179.425, "dur": 0.813, + "args": { + "External id": 4730713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360652181.927, "dur": 1.184, + "args": { + "External id": 4730714,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360652200.687, "dur": 152.085, + "args": { + "External id": 4730715,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360652216.811, "dur": 128.693, + "args": { + "External id": 4730716,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360652233.112, "dur": 12.042, + "args": { + "External id": 4730717,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360652248.318, "dur": 70.690, + "args": { + "External id": 4730718,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360652252.817, "dur": 65.810, + "args": { + "External id": 4730719,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652256.764, "dur": 7.532, + "args": { + "External id": 4730720,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360652266.164, "dur": 51.720, + "args": { + "External id": 4730721,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5472 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.0", "pid": 1336753, "tid": 1381210, + "ts": 1712360652477.896, "dur": 487.471, + "args": { + "External id": 4730722,"Record function id": 0, "Ev Idx": 5473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1712360652493.399, "dur": 460.857, + "args": { + "External id": 4730723,"Record function id": 0, "Ev Idx": 5474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360652554.154, "dur": 4.532, + "args": { + "External id": 4730724,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360652574.272, "dur": 26.585, + "args": { + "External id": 4730725,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652579.134, "dur": 1.524, + "args": { + "External id": 4730726,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652582.952, "dur": 0.517, + "args": { + "External id": 4730727,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652585.502, "dur": 0.430, + "args": { + "External id": 4730728,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652587.381, "dur": 0.587, + "args": { + "External id": 4730729,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652589.273, "dur": 0.719, + "args": { + "External id": 4730730,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652591.260, "dur": 0.455, + "args": { + "External id": 4730731,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652592.710, "dur": 2.166, + "args": { + "External id": 4730732,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652596.458, "dur": 0.349, + "args": { + "External id": 4730733,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652598.062, "dur": 0.396, + "args": { + "External id": 4730734,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360652609.879, "dur": 28.020, + "args": { + "External id": 4730735,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1381210, + "ts": 1712360652666.789, "dur": 89.126, + "args": { + "External id": 4730736,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 5487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360652676.003, "dur": 2.893, + "args": { + "External id": 4730737,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1381210, + "ts": 1712360652683.689, "dur": 9.726, + "args": { + "External id": 4730738,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1381210, + "ts": 1712360652687.747, "dur": 5.283, + "args": { + "External id": 4730739,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 5490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652690.960, "dur": 0.565, + "args": { + "External id": 4730740,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1381210, + "ts": 1712360652699.975, "dur": 22.564, + "args": { + "External id": 4730741,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652701.898, "dur": 0.517, + "args": { + "External id": 4730742,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652703.580, "dur": 0.525, + "args": { + "External id": 4730743,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652705.517, "dur": 0.290, + "args": { + "External id": 4730744,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652707.320, "dur": 1.727, + "args": { + "External id": 4730745,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652710.054, "dur": 0.157, + "args": { + "External id": 4730746,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652712.033, "dur": 0.308, + "args": { + "External id": 4730747,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652714.055, "dur": 0.365, + "args": { + "External id": 4730748,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652715.322, "dur": 0.278, + "args": { + "External id": 4730749,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360652716.875, "dur": 0.295, + "args": { + "External id": 4730750,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360652731.025, "dur": 18.227, + "args": { + "External id": 4730751,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360652797.336, "dur": 100.762, + "args": { + "External id": 4730752,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 5503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360652818.312, "dur": 76.728, + "args": { + "External id": 4730753,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5504, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360652826.852, "dur": 64.268, + "args": { + "External id": 4730754,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 5505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360652909.864, "dur": 1.860, + "args": { + "External id": 4730755,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5506, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360652979.598, "dur": 1601.055, + "args": { + "External id": 4730756,"Sequence number": 47018768, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5507 + } + }, + { + "ph": "f", "id": 224, "pid": 1336753, "tid": 1381210, "ts": 1712360652979.598, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360653146.792, "dur": 106.081, + "args": { + "External id": 4730757,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360653296.218, "dur": 37.522, + "args": { + "External id": 4730758,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360653350.476, "dur": 48.383, + "args": { + "External id": 4730759,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360653407.906, "dur": 31.629, + "args": { + "External id": 4730760,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360653445.538, "dur": 45.831, + "args": { + "External id": 4730761,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360653500.283, "dur": 28.624, + "args": { + "External id": 4730762,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360653535.681, "dur": 41.560, + "args": { + "External id": 4730763,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360653601.187, "dur": 22.527, + "args": { + "External id": 4730764,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360653640.873, "dur": 26.965, + "args": { + "External id": 4730765,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360653688.384, "dur": 18.118, + "args": { + "External id": 4730766,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360653718.324, "dur": 13.514, + "args": { + "External id": 4730767,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360653741.523, "dur": 26.687, + "args": { + "External id": 4730768,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360653771.397, "dur": 32.108, + "args": { + "External id": 4730769,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360653829.244, "dur": 202.530, + "args": { + "External id": 4730770,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360653902.791, "dur": 5.925, + "args": { + "External id": 4730771,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360653910.699, "dur": 2.077, + "args": { + "External id": 4730772,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360654081.906, "dur": 25.942, + "args": { + "External id": 4730773,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360654119.228, "dur": 14.840, + "args": { + "External id": 4730774,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360654143.950, "dur": 44.907, + "args": { + "External id": 4730775,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360654196.729, "dur": 36.956, + "args": { + "External id": 4730776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360654240.167, "dur": 19.625, + "args": { + "External id": 4730777,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360654264.817, "dur": 29.843, + "args": { + "External id": 4730778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360654300.337, "dur": 19.216, + "args": { + "External id": 4730779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360654331.201, "dur": 29.356, + "args": { + "External id": 4730780,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360654375.898, "dur": 24.039, + "args": { + "External id": 4730781,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360654421.631, "dur": 23.190, + "args": { + "External id": 4730782,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360654458.850, "dur": 16.787, + "args": { + "External id": 4730783,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360654489.054, "dur": 24.962, + "args": { + "External id": 4730784,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360654534.876, "dur": 18.132, + "args": { + "External id": 4730785,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654627.027, "dur": 15.182, + "args": { + "External id": 4730786,"Record function id": 0, "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654630.356, "dur": 10.901, + "args": { + "External id": 4730787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654634.388, "dur": 5.980, + "args": { + "External id": 4730788,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654636.189, "dur": 4.044, + "args": { + "External id": 4730789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654646.231, "dur": 4.674, + "args": { + "External id": 4730790,"Record function id": 0, "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654647.360, "dur": 3.125, + "args": { + "External id": 4730791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654648.005, "dur": 1.940, + "args": { + "External id": 4730792,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654648.869, "dur": 0.980, + "args": { + "External id": 4730793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654654.275, "dur": 4.889, + "args": { + "External id": 4730794,"Record function id": 0, "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654655.564, "dur": 3.189, + "args": { + "External id": 4730795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654656.430, "dur": 1.884, + "args": { + "External id": 4730796,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654657.056, "dur": 1.195, + "args": { + "External id": 4730797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654662.418, "dur": 3.851, + "args": { + "External id": 4730798,"Record function id": 0, "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654663.747, "dur": 2.102, + "args": { + "External id": 4730799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654664.464, "dur": 0.925, + "args": { + "External id": 4730800,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654664.815, "dur": 0.511, + "args": { + "External id": 4730801,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654672.665, "dur": 11.357, + "args": { + "External id": 4730802,"Record function id": 0, "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654673.791, "dur": 9.814, + "args": { + "External id": 4730803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654674.289, "dur": 2.818, + "args": { + "External id": 4730804,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654674.692, "dur": 2.351, + "args": { + "External id": 4730805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654687.189, "dur": 4.060, + "args": { + "External id": 4730806,"Record function id": 0, "Ev Idx": 5557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654688.335, "dur": 2.460, + "args": { + "External id": 4730807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654689.060, "dur": 1.307, + "args": { + "External id": 4730808,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654689.484, "dur": 0.784, + "args": { + "External id": 4730809,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654694.469, "dur": 3.329, + "args": { + "External id": 4730810,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654695.511, "dur": 1.881, + "args": { + "External id": 4730811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654695.975, "dur": 1.029, + "args": { + "External id": 4730812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654696.252, "dur": 0.677, + "args": { + "External id": 4730813,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654700.908, "dur": 3.877, + "args": { + "External id": 4730814,"Record function id": 0, "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654702.115, "dur": 2.256, + "args": { + "External id": 4730815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654702.995, "dur": 0.973, + "args": { + "External id": 4730816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654703.316, "dur": 0.555, + "args": { + "External id": 4730817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654707.897, "dur": 3.559, + "args": { + "External id": 4730818,"Record function id": 0, "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360654708.931, "dur": 2.103, + "args": { + "External id": 4730819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654709.463, "dur": 1.145, + "args": { + "External id": 4730820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360654709.902, "dur": 0.595, + "args": { + "External id": 4730821,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360654715.266, "dur": 38591.761, + "args": { + "External id": 4730822,"Record function id": 0, "Sequence number": 47018767, "Fwd thread id": 1, "Ev Idx": 5573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360654716.519, "dur": 38581.775, + "args": { + "External id": 4730823,"Sequence number": 47018767, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5574 + } + }, + { + "ph": "f", "id": 225, "pid": 1336753, "tid": 1381210, "ts": 1712360654716.519, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1712360654743.839, "dur": 36.486, + "args": { + "External id": 4730824,"Record function id": 0, "Ev Idx": 5575 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1712360654788.144, "dur": 65.690, + "args": { + "External id": 4730825,"Record function id": 0, "Ev Idx": 5576 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1712360654859.314, "dur": 38430.913, + "args": { + "External id": 4730826,"Record function id": 0, "Ev Idx": 5577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360654946.850, "dur": 6.506, + "args": { + "External id": 4730827,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360654962.062, "dur": 4.538, + "args": { + "External id": 4730828,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360654979.997, "dur": 37466.723, + "args": { + "External id": 4730829,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360655035.480, "dur": 37402.817, + "args": { + "External id": 4730830,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360655089.499, "dur": 14.400, + "args": { + "External id": 4730831,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360655113.737, "dur": 37283.607, + "args": { + "External id": 4730832,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360655116.970, "dur": 37279.540, + "args": { + "External id": 4730833,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360655120.864, "dur": 6.149, + "args": { + "External id": 4730834,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360655129.843, "dur": 37263.534, + "args": { + "External id": 4730835,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360692534.509, "dur": 8.508, + "args": { + "External id": 4730836,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360692537.415, "dur": 5.278, + "args": { + "External id": 4730837,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360692571.969, "dur": 387.094, + "args": { + "External id": 4730838,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360692598.835, "dur": 355.573, + "args": { + "External id": 4730839,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5590, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360692608.819, "dur": 339.785, + "args": { + "External id": 4730840,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360692976.385, "dur": 2.154, + "args": { + "External id": 4730841,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5592, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693089.270, "dur": 6.754, + "args": { + "External id": 4730842,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693140.307, "dur": 3.280, + "args": { + "External id": 4730843,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693158.134, "dur": 1.048, + "args": { + "External id": 4730844,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693170.266, "dur": 1.141, + "args": { + "External id": 4730845,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693182.483, "dur": 0.942, + "args": { + "External id": 4730846,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693192.346, "dur": 2.636, + "args": { + "External id": 4730847,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693205.845, "dur": 1.161, + "args": { + "External id": 4730848,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693217.159, "dur": 1.836, + "args": { + "External id": 4730849,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693229.008, "dur": 0.804, + "args": { + "External id": 4730850,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360693323.367, "dur": 2140.176, + "args": { + "External id": 4730851,"Record function id": 0, "Ev Idx": 5602 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1712360693343.362, "dur": 426.695, + "args": { + "External id": 4730852,"Record function id": 0, "Ev Idx": 5603 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1712360693357.710, "dur": 313.562, + "args": { + "External id": 4730853,"Record function id": 0, "Ev Idx": 5604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693442.015, "dur": 3.891, + "args": { + "External id": 4730854,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693448.727, "dur": 0.860, + "args": { + "External id": 4730855,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693451.182, "dur": 2.876, + "args": { + "External id": 4730856,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693457.146, "dur": 0.770, + "args": { + "External id": 4730857,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693460.113, "dur": 0.966, + "args": { + "External id": 4730858,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693462.511, "dur": 1.216, + "args": { + "External id": 4730859,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693465.060, "dur": 0.901, + "args": { + "External id": 4730860,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693471.044, "dur": 1.086, + "args": { + "External id": 4730861,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693473.430, "dur": 0.899, + "args": { + "External id": 4730862,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360693475.750, "dur": 0.742, + "args": { + "External id": 4730863,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360693493.549, "dur": 151.427, + "args": { + "External id": 4730864,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360693510.907, "dur": 130.270, + "args": { + "External id": 4730865,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360693529.760, "dur": 14.507, + "args": { + "External id": 4730866,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360693547.029, "dur": 67.328, + "args": { + "External id": 4730867,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360693549.907, "dur": 64.038, + "args": { + "External id": 4730868,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360693553.809, "dur": 5.733, + "args": { + "External id": 4730869,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360693561.441, "dur": 51.667, + "args": { + "External id": 4730870,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360693777.042, "dur": 1665.623, + "args": { + "External id": 4730871,"Sequence number": 47018766, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5622 + } + }, + { + "ph": "f", "id": 226, "pid": 1336753, "tid": 1381210, "ts": 1712360693777.042, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360693879.125, "dur": 146.336, + "args": { + "External id": 4730872,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360694082.919, "dur": 45.606, + "args": { + "External id": 4730873,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336753, "tid": 1381210, + "ts": 1712360694147.351, "dur": 58.345, + "args": { + "External id": 4730874,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360694217.170, "dur": 32.098, + "args": { + "External id": 4730875,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360694256.473, "dur": 44.541, + "args": { + "External id": 4730876,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360694307.772, "dur": 27.487, + "args": { + "External id": 4730877,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360694342.241, "dur": 41.797, + "args": { + "External id": 4730878,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360694405.590, "dur": 21.181, + "args": { + "External id": 4730879,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360694444.700, "dur": 28.318, + "args": { + "External id": 4730880,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360694564.398, "dur": 22.231, + "args": { + "External id": 4730881,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360694599.770, "dur": 13.650, + "args": { + "External id": 4730882,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360694622.568, "dur": 31.434, + "args": { + "External id": 4730883,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360694657.362, "dur": 32.781, + "args": { + "External id": 4730884,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336753, "tid": 1381210, + "ts": 1712360694723.262, "dur": 163.165, + "args": { + "External id": 4730885,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360694796.883, "dur": 5.817, + "args": { + "External id": 4730886,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360694804.763, "dur": 2.307, + "args": { + "External id": 4730887,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360694917.814, "dur": 23.172, + "args": { + "External id": 4730888,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360694951.393, "dur": 14.470, + "args": { + "External id": 4730889,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360694972.931, "dur": 74.052, + "args": { + "External id": 4730890,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360695056.443, "dur": 56.798, + "args": { + "External id": 4730891,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360695122.845, "dur": 20.929, + "args": { + "External id": 4730892,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360695150.678, "dur": 32.997, + "args": { + "External id": 4730893,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360695189.760, "dur": 19.293, + "args": { + "External id": 4730894,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1712360695216.518, "dur": 29.758, + "args": { + "External id": 4730895,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336753, "tid": 1381210, + "ts": 1712360695263.211, "dur": 21.465, + "args": { + "External id": 4730896,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360695301.721, "dur": 26.943, + "args": { + "External id": 4730897,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360695342.633, "dur": 16.347, + "args": { + "External id": 4730898,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336753, "tid": 1381210, + "ts": 1712360695372.887, "dur": 17.090, + "args": { + "External id": 4730899,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336753, "tid": 1381210, + "ts": 1712360695400.389, "dur": 15.159, + "args": { + "External id": 4730900,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695485.869, "dur": 14.742, + "args": { + "External id": 4730901,"Record function id": 0, "Ev Idx": 5652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695489.080, "dur": 10.618, + "args": { + "External id": 4730902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695493.361, "dur": 5.564, + "args": { + "External id": 4730903,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695494.986, "dur": 3.826, + "args": { + "External id": 4730904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695504.478, "dur": 4.619, + "args": { + "External id": 4730905,"Record function id": 0, "Ev Idx": 5656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695505.810, "dur": 2.843, + "args": { + "External id": 4730906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695506.631, "dur": 1.563, + "args": { + "External id": 4730907,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695507.223, "dur": 0.878, + "args": { + "External id": 4730908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695512.436, "dur": 4.193, + "args": { + "External id": 4730909,"Record function id": 0, "Ev Idx": 5660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695514.008, "dur": 2.230, + "args": { + "External id": 4730910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695514.658, "dur": 1.153, + "args": { + "External id": 4730911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695515.081, "dur": 0.666, + "args": { + "External id": 4730912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695519.867, "dur": 3.833, + "args": { + "External id": 4730913,"Record function id": 0, "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695521.047, "dur": 2.270, + "args": { + "External id": 4730914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695521.644, "dur": 1.112, + "args": { + "External id": 4730915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695521.959, "dur": 0.732, + "args": { + "External id": 4730916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695526.877, "dur": 4.324, + "args": { + "External id": 4730917,"Record function id": 0, "Ev Idx": 5668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695528.354, "dur": 2.442, + "args": { + "External id": 4730918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695528.877, "dur": 1.516, + "args": { + "External id": 4730919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695529.568, "dur": 0.755, + "args": { + "External id": 4730920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695534.399, "dur": 4.363, + "args": { + "External id": 4730921,"Record function id": 0, "Ev Idx": 5672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695535.603, "dur": 2.705, + "args": { + "External id": 4730922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695536.490, "dur": 1.378, + "args": { + "External id": 4730923,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695537.064, "dur": 0.703, + "args": { + "External id": 4730924,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695542.103, "dur": 5.040, + "args": { + "External id": 4730925,"Record function id": 0, "Ev Idx": 5676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695543.311, "dur": 3.405, + "args": { + "External id": 4730926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695543.845, "dur": 2.461, + "args": { + "External id": 4730927,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695544.143, "dur": 2.095, + "args": { + "External id": 4730928,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695550.352, "dur": 4.912, + "args": { + "External id": 4730929,"Record function id": 0, "Ev Idx": 5680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695551.825, "dur": 3.046, + "args": { + "External id": 4730930,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695552.638, "dur": 1.790, + "args": { + "External id": 4730931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695553.105, "dur": 1.215, + "args": { + "External id": 4730932,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695558.408, "dur": 4.543, + "args": { + "External id": 4730933,"Record function id": 0, "Ev Idx": 5684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360695559.856, "dur": 2.666, + "args": { + "External id": 4730934,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695560.722, "dur": 1.383, + "args": { + "External id": 4730935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360695561.155, "dur": 0.839, + "args": { + "External id": 4730936,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360695567.408, "dur": 36643.081, + "args": { + "External id": 4730937,"Record function id": 0, "Sequence number": 47018765, "Fwd thread id": 1, "Ev Idx": 5688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360695568.584, "dur": 36633.434, + "args": { + "External id": 4730938,"Sequence number": 47018765, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5689 + } + }, + { + "ph": "f", "id": 227, "pid": 1336753, "tid": 1381210, "ts": 1712360695568.584, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1712360695594.914, "dur": 36.148, + "args": { + "External id": 4730939,"Record function id": 0, "Ev Idx": 5690 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1712360695637.614, "dur": 70.459, + "args": { + "External id": 4730940,"Record function id": 0, "Ev Idx": 5691 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1712360695713.614, "dur": 36479.811, + "args": { + "External id": 4730941,"Record function id": 0, "Ev Idx": 5692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360695816.976, "dur": 7.526, + "args": { + "External id": 4730942,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360695834.787, "dur": 8.126, + "args": { + "External id": 4730943,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360695857.520, "dur": 35538.643, + "args": { + "External id": 4730944,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360695870.659, "dur": 35517.174, + "args": { + "External id": 4730945,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360695923.196, "dur": 13.219, + "args": { + "External id": 4730946,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360695945.833, "dur": 35405.120, + "args": { + "External id": 4730947,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360695948.400, "dur": 35401.804, + "args": { + "External id": 4730948,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360695952.651, "dur": 5.096, + "args": { + "External id": 4730949,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360695959.470, "dur": 35387.641, + "args": { + "External id": 4730950,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360731482.580, "dur": 8.823, + "args": { + "External id": 4730951,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360731485.369, "dur": 5.704, + "args": { + "External id": 4730952,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360731521.651, "dur": 340.119, + "args": { + "External id": 4730953,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360731547.739, "dur": 309.763, + "args": { + "External id": 4730954,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "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": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5705, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360731558.026, "dur": 293.684, + "args": { + "External id": 4730955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360731878.449, "dur": 2.161, + "args": { + "External id": 4730956,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5707, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360731932.194, "dur": 6.273, + "args": { + "External id": 4730957,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360731979.940, "dur": 36.201, + "args": { + "External id": 4730958,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360732036.715, "dur": 3.245, + "args": { + "External id": 4730959,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360732051.855, "dur": 1.022, + "args": { + "External id": 4730960,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360732064.150, "dur": 14.754, + "args": { + "External id": 4730961,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360732093.396, "dur": 1.187, + "args": { + "External id": 4730962,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360732105.616, "dur": 2.574, + "args": { + "External id": 4730963,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360732118.390, "dur": 1.330, + "args": { + "External id": 4730964,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360732129.119, "dur": 0.856, + "args": { + "External id": 4730965,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360732229.398, "dur": 262.858, + "args": { + "External id": 4730966,"Record function id": 0, "Sequence number": 47018764, "Fwd thread id": 1, "Ev Idx": 5717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1712360732232.488, "dur": 252.809, + "args": { + "External id": 4730967,"Sequence number": 47018764, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5718 + } + }, + { + "ph": "f", "id": 228, "pid": 1336753, "tid": 1381210, "ts": 1712360732232.488, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 1336753, "tid": 1381210, + "ts": 1712360732350.026, "dur": 44.085, + "args": { + "External id": 4730968,"kernel_hash": "cfr73mqqwqpdrss7r6csecalgrfowe5r3r24yaeyivzpezfoy4fz", "grid": "grid(65536000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "65536000"], "kernel_file": "/tmp/torchinductor_cvm/fr/cfr73mqqwqpdrss7r6csecalgrfowe5r3r24yaeyivzpezfoy4fz.py", "kernel_backend": "triton", "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_1", "pid": 1336753, "tid": 1381210, + "ts": 1712360732409.041, "dur": 27.098, + "args": { + "External id": 4730969,"kernel_hash": "cxedqnbrx2bvln4bf3pphdmthxjm6nsxqowbdddlxye4bt3yfnsg", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/xe/cxedqnbrx2bvln4bf3pphdmthxjm6nsxqowbdddlxye4bt3yfnsg.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096], [16, 4096, 2048], [32000, 2048], []], "Ev Idx": 5720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_2", "pid": 1336753, "tid": 1381210, + "ts": 1712360732451.963, "dur": 19.347, + "args": { + "External id": 4730970,"kernel_hash": "c2xxuncnwkfhjvqk7hfnejnsljjkm6qo4ajwnumdr7vdpf4nk2iq", "grid": "grid(65536000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "65536000"], "kernel_file": "/tmp/torchinductor_cvm/2x/c2xxuncnwkfhjvqk7hfnejnsljjkm6qo4ajwnumdr7vdpf4nk2iq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 5721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360732501.908, "dur": 14.157, + "args": { + "External id": 4730971,"Record function id": 0, "Ev Idx": 5722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1712360732504.783, "dur": 10.407, + "args": { + "External id": 4730972,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 5723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360732508.555, "dur": 5.752, + "args": { + "External id": 4730973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 5724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1381210, + "ts": 1712360732510.129, "dur": 4.036, + "args": { + "External id": 4730974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 5725 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_post_backward_callback", "pid": 1336753, "tid": 1381210, + "ts": 1712360732539.357, "dur": 7815.182, + "args": { + "External id": 4730975,"Record function id": 0, "Ev Idx": 5726 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 1336753, "tid": 1381210, + "ts": 1712360732558.113, "dur": 40.441, + "args": { + "External id": 4730976,"Record function id": 0, "Ev Idx": 5727 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 1336753, "tid": 1381210, + "ts": 1712360732604.593, "dur": 260.685, + "args": { + "External id": 4730977,"Record function id": 0, "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 1336753, "tid": 1381210, + "ts": 1712360732871.195, "dur": 7211.397, + "args": { + "External id": 4730978,"Record function id": 0, "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360733022.388, "dur": 7.888, + "args": { + "External id": 4730979,"Record function id": 0, "Concrete Inputs": ["[336611328]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1712360733042.049, "dur": 5.527, + "args": { + "External id": 4730980,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[336611328], []], "Ev Idx": 5731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360733081.835, "dur": 5734.280, + "args": { + "External id": 4730981,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [42076416, 1]], "Input Dims": [[], [], [], [8, 42076416]], "Ev Idx": 5732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336753, "tid": 1381210, + "ts": 1712360733101.285, "dur": 5701.786, + "args": { + "External id": 4730982,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [42076416, 1]], "Input Dims": [[], [], [], [8, 42076416]], "Ev Idx": 5733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360733454.749, "dur": 17.848, + "args": { + "External id": 4730983,"Record function id": 0, "Concrete Inputs": ["[82421]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1381210, + "ts": 1712360733534.205, "dur": 5223.663, + "args": { + "External id": 4730984,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[82421], [], [], [], [], [], [], []], "Ev Idx": 5735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1381210, + "ts": 1712360733537.358, "dur": 5219.427, + "args": { + "External id": 4730985,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[82421], [], [], [], [], [], []], "Ev Idx": 5736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360733542.371, "dur": 12.645, + "args": { + "External id": 4730986,"Record function id": 0, "Concrete Inputs": ["[82421]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1381210, + "ts": 1712360733557.124, "dur": 5194.580, + "args": { + "External id": 4730987,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[82421], [82421], []], "Ev Idx": 5738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360738944.204, "dur": 11.057, + "args": { + "External id": 4730988,"Record function id": 0, "Concrete Inputs": ["", "[42076416]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[336611328], [], [], [], [], []], "Ev Idx": 5739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1712360738948.363, "dur": 6.514, + "args": { + "External id": 4730989,"Record function id": 0, "Concrete Inputs": ["[42076416]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336753, "tid": 1381210, + "ts": 1712360739014.773, "dur": 391.283, + "args": { + "External id": 4730990,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[42076416], [336611328], [], [], [], []], "Ev Idx": 5741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360739038.859, "dur": 362.275, + "args": { + "External id": 4730991,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 42076416, "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": [[336611328], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5742, "In msg nelems": 336611328 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336753, "tid": 1381210, + "ts": 1712360739053.517, "dur": 341.690, + "args": { + "External id": 4730992,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[336611328]], "Ev Idx": 5743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1381210, + "ts": 1712360739424.981, "dur": 2.312, + "args": { + "External id": 4730993,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5744, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739486.563, "dur": 6.822, + "args": { + "External id": 4730994,"Record function id": 0, "Concrete Inputs": ["", "[4000, 2048]", "[2048, 1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739534.839, "dur": 1.323, + "args": { + "External id": 4730995,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "8192000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739549.822, "dur": 1.946, + "args": { + "External id": 4730996,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "8192256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739563.044, "dur": 2.898, + "args": { + "External id": 4730997,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "8716544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739576.215, "dur": 1.684, + "args": { + "External id": 4730998,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "9240832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739588.065, "dur": 1.373, + "args": { + "External id": 4730999,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "9765120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739601.684, "dur": 1.208, + "args": { + "External id": 4731000,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "10289408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739612.907, "dur": 2.710, + "args": { + "External id": 4731001,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "10289664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739625.856, "dur": 1.587, + "args": { + "External id": 4731002,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "11731456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739636.921, "dur": 1.180, + "args": { + "External id": 4731003,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "13173248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739648.008, "dur": 1.586, + "args": { + "External id": 4731004,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "14615040"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739659.083, "dur": 2.536, + "args": { + "External id": 4731005,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "14615296"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739671.654, "dur": 1.547, + "args": { + "External id": 4731006,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "15139584"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739683.413, "dur": 1.209, + "args": { + "External id": 4731007,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "15663872"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739695.324, "dur": 1.409, + "args": { + "External id": 4731008,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "16188160"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739706.235, "dur": 2.818, + "args": { + "External id": 4731009,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "16712448"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739718.512, "dur": 1.046, + "args": { + "External id": 4731010,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "16712704"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739729.425, "dur": 1.425, + "args": { + "External id": 4731011,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "18154496"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739741.108, "dur": 1.577, + "args": { + "External id": 4731012,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "19596288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739752.176, "dur": 2.544, + "args": { + "External id": 4731013,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21038080"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739764.126, "dur": 1.272, + "args": { + "External id": 4731014,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "21038336"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739775.405, "dur": 1.364, + "args": { + "External id": 4731015,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "21562624"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739786.786, "dur": 1.622, + "args": { + "External id": 4731016,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "22086912"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739799.282, "dur": 2.727, + "args": { + "External id": 4731017,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "22611200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739812.391, "dur": 1.350, + "args": { + "External id": 4731018,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "23135488"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739823.842, "dur": 1.594, + "args": { + "External id": 4731019,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "23135744"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739836.577, "dur": 1.214, + "args": { + "External id": 4731020,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "24577536"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739847.640, "dur": 2.575, + "args": { + "External id": 4731021,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "26019328"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739859.248, "dur": 1.319, + "args": { + "External id": 4731022,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "27461120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739870.403, "dur": 1.292, + "args": { + "External id": 4731023,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "27461376"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739881.124, "dur": 1.133, + "args": { + "External id": 4731024,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "27985664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739891.276, "dur": 2.668, + "args": { + "External id": 4731025,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "28509952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739904.047, "dur": 1.290, + "args": { + "External id": 4731026,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "29034240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739914.627, "dur": 1.646, + "args": { + "External id": 4731027,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "29558528"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739926.999, "dur": 1.723, + "args": { + "External id": 4731028,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "29558784"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739938.576, "dur": 2.757, + "args": { + "External id": 4731029,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "31000576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739950.762, "dur": 1.305, + "args": { + "External id": 4731030,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "32442368"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739961.635, "dur": 1.782, + "args": { + "External id": 4731031,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "33884160"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1712360739972.008, "dur": 1.570, + "args": { + "External id": 4731032,"Record function id": 0, "Concrete Inputs": ["", "[4000, 2048]", "[2048, 1]", "33884416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5783 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "ProfilerStep#195583", "pid": 1336753, "tid": 1336753, + "ts": 1712358641198.542, "dur": 2118693.288, + "args": { + "External id": 4720129,"Record function id": 0, "Ev Idx": 5784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 1336753, "tid": 1336753, + "ts": 1712358641235.111, "dur": 700.594, + "args": { + "External id": 4720130,"Record function id": 0, "Ev Idx": 5785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 1336753, "tid": 1336753, + "ts": 1712358641975.707, "dur": 2342.632, + "args": { + "External id": 4720131,"Record function id": 0, "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358643048.431, "dur": 7.534, + "args": { + "External id": 4720132,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 1336753, "tid": 1336753, + "ts": 1712358643120.524, "dur": 6.582, + "args": { + "External id": 4720133,"Sequence number": 47018764, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[16, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 5788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358643633.963, "dur": 2.777, + "args": { + "External id": 4720134,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 1336753, "tid": 1336753, + "ts": 1712358643647.699, "dur": 2.524, + "args": { + "External id": 4720135,"Sequence number": 47018764, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[16, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 5790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358644206.438, "dur": 2.397, + "args": { + "External id": 4720136,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 1336753, "tid": 1336753, + "ts": 1712358644213.563, "dur": 2.498, + "args": { + "External id": 4720137,"Sequence number": 47018764, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[16, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 5792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358645116.358, "dur": 16.602, + "args": { + "External id": 4720138,"Sequence number": 47018764, "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": [[16, 8192], [], [], [], []], "Ev Idx": 5793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358645127.058, "dur": 2.263, + "args": { + "External id": 4720139,"Record function id": 0, "Concrete Inputs": ["", "[16, 8192]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 5794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358645134.694, "dur": 4.452, + "args": { + "External id": 4720140,"Sequence number": 47018764, "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": [[16, 8192], [], [], [], []], "Ev Idx": 5795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358645136.915, "dur": 1.153, + "args": { + "External id": 4720141,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 5796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358645166.369, "dur": 519.381, + "args": { + "External id": 4720142,"Sequence number": 47018764, "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": [[16, 4096], [], [], [], [], [], [], []], "Ev Idx": 5797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358645173.036, "dur": 512.233, + "args": { + "External id": 4720143,"Sequence number": 47018764, "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": [[16, 4096], [], [], [], [], [], []], "Ev Idx": 5798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358645181.160, "dur": 9.809, + "args": { + "External id": 4720144,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "[4096, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358645193.270, "dur": 490.253, + "args": { + "External id": 4720145,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 5800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358645202.728, "dur": 0.705, + "args": { + "External id": 4720146,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 5801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358645205.930, "dur": 5.952, + "args": { + "External id": 4720147,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[8192, 1], [4096, 1]], "Input Dims": [[16, 4096], [16, 4096]], "Ev Idx": 5802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 1336753, "tid": 1336753, + "ts": 1712358645208.175, "dur": 3.527, + "args": { + "External id": 4720148,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], []], "Input Dims": [[16, 4096], [], []], "Ev Idx": 5803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358645210.713, "dur": 0.627, + "args": { + "External id": 4720149,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 5804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1712358645213.816, "dur": 225.420, + "args": { + "External id": 4720150,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 5805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712358645218.580, "dur": 220.236, + "args": { + "External id": 4720151,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 5806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358645220.929, "dur": 16.957, + "args": { + "External id": 4720152,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 5807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358645223.432, "dur": 13.878, + "args": { + "External id": 4720153,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358645238.909, "dur": 199.379, + "args": { + "External id": 4720154,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 5809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358645441.166, "dur": 238.468, + "args": { + "External id": 4720155,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 5810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358645696.520, "dur": 706.692, + "args": { + "External id": 4720156,"Sequence number": 47018764, "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": [[16, 8192], [], [], [], [], [], [], []], "Ev Idx": 5811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358645698.099, "dur": 704.160, + "args": { + "External id": 4720157,"Sequence number": 47018764, "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": [[16, 8192], [], [], [], [], [], []], "Ev Idx": 5812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358645707.027, "dur": 7.160, + "args": { + "External id": 4720158,"Record function id": 0, "Concrete Inputs": ["[16, 8192]", "[8192, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358645715.058, "dur": 683.195, + "args": { + "External id": 4720159,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[8192, 1], [8192, 1], []], "Input Dims": [[16, 8192], [16, 8192], []], "Ev Idx": 5814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 1336753, "tid": 1336753, + "ts": 1712358646434.380, "dur": 52.041, + "args": { + "External id": 4720160,"Record function id": 0, "Concrete Inputs": ["0", "4096", "", "", "", "False"], "Input type": ["Scalar", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358646440.542, "dur": 5.749, + "args": { + "External id": 4720161,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 1336753, "tid": 1336753, + "ts": 1712358646448.719, "dur": 37.378, + "args": { + "External id": 4720162,"Record function id": 0, "Concrete Inputs": ["0", "4096", "1", ""], "Input type": ["Scalar", "Scalar", "Scalar", "long int"], "Input Strides": [[], [], [], [1]], "Input Dims": [[], [], [], [0]], "Ev Idx": 5817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712358646453.237, "dur": 6.380, + "args": { + "External id": 4720163,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["long int", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 5818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::repeat", "pid": 1336753, "tid": 1336753, + "ts": 1712358646498.102, "dur": 79.193, + "args": { + "External id": 4720164,"Sequence number": 47018764, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 1336753, "tid": 1336753, + "ts": 1712358646506.601, "dur": 8.198, + "args": { + "External id": 4720165,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[4096], [], []], "Ev Idx": 5820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358646512.756, "dur": 1.689, + "args": { + "External id": 4720166,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "[4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 5821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358646516.042, "dur": 4.914, + "args": { + "External id": 4720167,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1712358646523.355, "dur": 5.022, + "args": { + "External id": 4720168,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[4096, 1]], "Input Dims": [[16, 4096]], "Ev Idx": 5823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 1336753, "tid": 1336753, + "ts": 1712358646530.710, "dur": 5.298, + "args": { + "External id": 4720169,"Record function id": 0, "Concrete Inputs": ["", "0", "1", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 5824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358646535.205, "dur": 0.648, + "args": { + "External id": 4720170,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1]", "[4096, 1, 4096]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 5825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 1336753, "tid": 1336753, + "ts": 1712358646536.765, "dur": 4.725, + "args": { + "External id": 4720171,"Record function id": 0, "Concrete Inputs": ["", "1", "4096", "4096"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[16, 4096, 1], [], [], []], "Ev Idx": 5826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358646540.381, "dur": 1.027, + "args": { + "External id": 4720172,"Record function id": 0, "Concrete Inputs": ["", "[16, 1, 1, 4096]", "[4096, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[16, 4096, 1], [], [], []], "Ev Idx": 5827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358646543.087, "dur": 6.954, + "args": { + "External id": 4720173,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[4096, 1], [4096, 4096, 4096, 1]], "Input Dims": [[1, 4096], [16, 1, 1, 4096]], "Ev Idx": 5828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 1336753, "tid": 1336753, + "ts": 1712358646546.698, "dur": 3.227, + "args": { + "External id": 4720174,"Record function id": 0, "Concrete Inputs": ["", "[16, 1, 1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1, 4096], [], []], "Ev Idx": 5829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358646548.593, "dur": 1.030, + "args": { + "External id": 4720175,"Record function id": 0, "Concrete Inputs": ["", "[16, 1, 1, 4096]", "[0, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 5830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358646550.865, "dur": 25.772, + "args": { + "External id": 4720176,"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": [[16, 1, 1, 4096], [16, 1, 1, 4096], []], "Ev Idx": 5831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358646585.282, "dur": 29.869, + "args": { + "External id": 4720177,"Sequence number": 47018764, "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": [[16, 4096], [], [], [], []], "Ev Idx": 5832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358646586.933, "dur": 28.039, + "args": { + "External id": 4720178,"Sequence number": 47018764, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], [], []], "Ev Idx": 5833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358646593.650, "dur": 3.319, + "args": { + "External id": 4720179,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "[4096, 1]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358646597.721, "dur": 16.592, + "args": { + "External id": 4720180,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 5835 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_pre_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358646731.890, "dur": 151.629, + "args": { + "External id": 4720181,"Record function id": 0, "Ev Idx": 5836 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 1336753, "tid": 1336753, + "ts": 1712358646814.469, "dur": 58.754, + "args": { + "External id": 4720182,"Record function id": 0, "Ev Idx": 5837 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358646891.139, "dur": 43.125, + "args": { + "External id": 4720183,"Record function id": 0, "Ev Idx": 5838 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358646942.276, "dur": 8202.148, + "args": { + "External id": 4720184,"Record function id": 0, "Ev Idx": 5839 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 1336753, "tid": 1336753, + "ts": 1712358646952.832, "dur": 1417.770, + "args": { + "External id": 4720185,"Record function id": 0, "Ev Idx": 5840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358647135.592, "dur": 8.659, + "args": { + "External id": 4720186,"Record function id": 0, "Concrete Inputs": ["[42076416]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358647164.243, "dur": 133.276, + "args": { + "External id": 4720187,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[42076416], [], []], "Ev Idx": 5842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647168.971, "dur": 1.904, + "args": { + "External id": 4720188,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647177.263, "dur": 0.418, + "args": { + "External id": 4720189,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "8192000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647178.471, "dur": 0.573, + "args": { + "External id": 4720190,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8192256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647179.869, "dur": 2.079, + "args": { + "External id": 4720191,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8716544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647185.283, "dur": 0.531, + "args": { + "External id": 4720192,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9240832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647186.309, "dur": 0.462, + "args": { + "External id": 4720193,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9765120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647187.491, "dur": 2.516, + "args": { + "External id": 4720194,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "10289408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647193.356, "dur": 0.328, + "args": { + "External id": 4720195,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "10289664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647194.360, "dur": 0.651, + "args": { + "External id": 4720196,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "11731456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647201.467, "dur": 0.182, + "args": { + "External id": 4720197,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "13173248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647202.213, "dur": 0.716, + "args": { + "External id": 4720198,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "14615040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647203.595, "dur": 2.026, + "args": { + "External id": 4720199,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "14615296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647210.428, "dur": 0.339, + "args": { + "External id": 4720200,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15139584"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647211.235, "dur": 0.353, + "args": { + "External id": 4720201,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15663872"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647212.151, "dur": 2.615, + "args": { + "External id": 4720202,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "16188160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647218.235, "dur": 0.162, + "args": { + "External id": 4720203,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "16712448"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647219.156, "dur": 0.281, + "args": { + "External id": 4720204,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "16712704"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647225.320, "dur": 0.280, + "args": { + "External id": 4720205,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "18154496"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647226.132, "dur": 0.435, + "args": { + "External id": 4720206,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "19596288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647227.145, "dur": 2.120, + "args": { + "External id": 4720207,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21038080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647232.444, "dur": 0.349, + "args": { + "External id": 4720208,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21038336"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647233.307, "dur": 0.440, + "args": { + "External id": 4720209,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21562624"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647234.450, "dur": 2.140, + "args": { + "External id": 4720210,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22086912"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647239.677, "dur": 0.364, + "args": { + "External id": 4720211,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22611200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647240.882, "dur": 0.261, + "args": { + "External id": 4720212,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "23135488"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647245.972, "dur": 0.174, + "args": { + "External id": 4720213,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "23135744"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647246.779, "dur": 0.282, + "args": { + "External id": 4720214,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24577536"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647247.864, "dur": 1.653, + "args": { + "External id": 4720215,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "26019328"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647253.046, "dur": 0.178, + "args": { + "External id": 4720216,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "27461120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647253.865, "dur": 0.443, + "args": { + "External id": 4720217,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27461376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647255.048, "dur": 2.504, + "args": { + "External id": 4720218,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27985664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647260.574, "dur": 0.365, + "args": { + "External id": 4720219,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "28509952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647261.667, "dur": 0.148, + "args": { + "External id": 4720220,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29034240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647266.928, "dur": 0.329, + "args": { + "External id": 4720221,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "29558528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647267.857, "dur": 0.555, + "args": { + "External id": 4720222,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "29558784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647268.890, "dur": 2.147, + "args": { + "External id": 4720223,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "31000576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647274.105, "dur": 0.493, + "args": { + "External id": 4720224,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "32442368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647275.218, "dur": 0.498, + "args": { + "External id": 4720225,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "33884160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647276.349, "dur": 2.319, + "args": { + "External id": 4720226,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "33884416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358647325.374, "dur": 84.629, + "args": { + "External id": 4720227,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358647488.980, "dur": 273.095, + "args": { + "External id": 4720228,"Record function id": 0, "Concrete Inputs": ["", "", "42076416", "8", "0", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358647504.669, "dur": 4.566, + "args": { + "External id": 4720229,"Record function id": 0, "Concrete Inputs": ["[336611328]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358647515.292, "dur": 14.010, + "args": { + "External id": 4720230,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "42076416"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[336611328], [], [], []], "Ev Idx": 5885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358647519.703, "dur": 9.158, + "args": { + "External id": 4720231,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "42076416", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[336611328], [], [], [], []], "Ev Idx": 5886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647525.750, "dur": 0.448, + "args": { + "External id": 4720232,"Record function id": 0, "Concrete Inputs": ["", "[42076416]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[336611328], [], [], []], "Ev Idx": 5887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358647536.859, "dur": 127.687, + "args": { + "External id": 4720233,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[42076416], [], []], "Ev Idx": 5888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647538.620, "dur": 0.356, + "args": { + "External id": 4720234,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647540.318, "dur": 0.304, + "args": { + "External id": 4720235,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "8192000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647544.011, "dur": 2.259, + "args": { + "External id": 4720236,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8192256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647547.143, "dur": 0.672, + "args": { + "External id": 4720237,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8716544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647550.389, "dur": 0.301, + "args": { + "External id": 4720238,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9240832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647551.217, "dur": 0.270, + "args": { + "External id": 4720239,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9765120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647552.346, "dur": 0.471, + "args": { + "External id": 4720240,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "10289408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647555.840, "dur": 0.442, + "args": { + "External id": 4720241,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "10289664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647556.986, "dur": 0.954, + "args": { + "External id": 4720242,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "11731456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647558.944, "dur": 0.169, + "args": { + "External id": 4720243,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "13173248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647562.653, "dur": 1.894, + "args": { + "External id": 4720244,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "14615040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647565.548, "dur": 0.455, + "args": { + "External id": 4720245,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "14615296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647569.340, "dur": 2.791, + "args": { + "External id": 4720246,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15139584"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647572.933, "dur": 0.364, + "args": { + "External id": 4720247,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15663872"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647574.013, "dur": 0.387, + "args": { + "External id": 4720248,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "16188160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647579.408, "dur": 0.173, + "args": { + "External id": 4720249,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "16712448"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647580.212, "dur": 0.280, + "args": { + "External id": 4720250,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "16712704"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647581.190, "dur": 0.338, + "args": { + "External id": 4720251,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "18154496"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647587.373, "dur": 2.331, + "args": { + "External id": 4720252,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "19596288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647590.717, "dur": 0.190, + "args": { + "External id": 4720253,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21038080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647593.885, "dur": 2.657, + "args": { + "External id": 4720254,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21038336"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647597.493, "dur": 0.194, + "args": { + "External id": 4720255,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21562624"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647598.283, "dur": 0.295, + "args": { + "External id": 4720256,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22086912"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647603.353, "dur": 0.267, + "args": { + "External id": 4720257,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22611200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647604.175, "dur": 0.472, + "args": { + "External id": 4720258,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "23135488"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647605.680, "dur": 0.153, + "args": { + "External id": 4720259,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "23135744"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647611.416, "dur": 1.412, + "args": { + "External id": 4720260,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24577536"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647613.626, "dur": 0.387, + "args": { + "External id": 4720261,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "26019328"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647617.235, "dur": 2.338, + "args": { + "External id": 4720262,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "27461120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647620.043, "dur": 0.175, + "args": { + "External id": 4720263,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27461376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647620.757, "dur": 0.145, + "args": { + "External id": 4720264,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27985664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647626.377, "dur": 3.944, + "args": { + "External id": 4720265,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "28509952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647630.948, "dur": 0.404, + "args": { + "External id": 4720266,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29034240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647632.092, "dur": 0.334, + "args": { + "External id": 4720267,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "29558528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647637.524, "dur": 1.399, + "args": { + "External id": 4720268,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "29558784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647639.491, "dur": 0.473, + "args": { + "External id": 4720269,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "31000576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647642.743, "dur": 2.341, + "args": { + "External id": 4720270,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "32442368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647645.781, "dur": 0.184, + "args": { + "External id": 4720271,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "33884160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358647646.529, "dur": 0.431, + "args": { + "External id": 4720272,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "33884416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358647687.020, "dur": 59.376, + "args": { + "External id": 4720273,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358647817.405, "dur": 433.921, + "args": { + "External id": 4720274,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[336611328], [42076416], [], [], []], "Ev Idx": 5929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358647851.236, "dur": 395.009, + "args": { + "External id": 4720275,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 336611328, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[42076416], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5930, "In msg nelems": 42076416 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358647861.497, "dur": 378.079, + "args": { + "External id": 4720276,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[42076416]], "Ev Idx": 5931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358648280.453, "dur": 2.471, + "args": { + "External id": 4720277,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5932, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 1336753, "tid": 1336753, + "ts": 1712358648387.074, "dur": 6508.380, + "args": { + "External id": 4720278,"Record function id": 0, "Ev Idx": 5933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648617.065, "dur": 6.814, + "args": { + "External id": 4720279,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[336611328], []], "Ev Idx": 5934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648627.536, "dur": 1.045, + "args": { + "External id": 4720280,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[65536000], []], "Ev Idx": 5935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648630.476, "dur": 1.068, + "args": { + "External id": 4720281,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648633.704, "dur": 2.092, + "args": { + "External id": 4720282,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648637.228, "dur": 1.056, + "args": { + "External id": 4720283,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648639.791, "dur": 1.032, + "args": { + "External id": 4720284,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648644.550, "dur": 0.929, + "args": { + "External id": 4720285,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648646.617, "dur": 2.361, + "args": { + "External id": 4720286,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648653.170, "dur": 0.920, + "args": { + "External id": 4720287,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648655.323, "dur": 0.936, + "args": { + "External id": 4720288,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648660.027, "dur": 0.930, + "args": { + "External id": 4720289,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648662.287, "dur": 1.801, + "args": { + "External id": 4720290,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648665.729, "dur": 0.787, + "args": { + "External id": 4720291,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648668.003, "dur": 0.870, + "args": { + "External id": 4720292,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648672.599, "dur": 0.749, + "args": { + "External id": 4720293,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648674.683, "dur": 2.274, + "args": { + "External id": 4720294,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648681.289, "dur": 0.548, + "args": { + "External id": 4720295,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648683.495, "dur": 1.027, + "args": { + "External id": 4720296,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648688.202, "dur": 0.824, + "args": { + "External id": 4720297,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648690.788, "dur": 2.307, + "args": { + "External id": 4720298,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648694.534, "dur": 0.760, + "args": { + "External id": 4720299,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648696.715, "dur": 0.795, + "args": { + "External id": 4720300,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648701.407, "dur": 0.546, + "args": { + "External id": 4720301,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648703.479, "dur": 1.722, + "args": { + "External id": 4720302,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648724.843, "dur": 0.930, + "args": { + "External id": 4720303,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648727.332, "dur": 0.854, + "args": { + "External id": 4720304,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648731.782, "dur": 0.897, + "args": { + "External id": 4720305,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648734.266, "dur": 2.371, + "args": { + "External id": 4720306,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648738.310, "dur": 0.675, + "args": { + "External id": 4720307,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648740.319, "dur": 0.698, + "args": { + "External id": 4720308,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648744.152, "dur": 0.760, + "args": { + "External id": 4720309,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648746.272, "dur": 2.362, + "args": { + "External id": 4720310,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648752.735, "dur": 0.655, + "args": { + "External id": 4720311,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648754.863, "dur": 0.898, + "args": { + "External id": 4720312,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648759.487, "dur": 0.797, + "args": { + "External id": 4720313,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648761.661, "dur": 1.982, + "args": { + "External id": 4720314,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648764.890, "dur": 0.857, + "args": { + "External id": 4720315,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648766.965, "dur": 0.642, + "args": { + "External id": 4720316,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648770.665, "dur": 0.799, + "args": { + "External id": 4720317,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358648772.922, "dur": 1.949, + "args": { + "External id": 4720318,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[65536000], []], "Ev Idx": 5973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358648803.929, "dur": 6039.068, + "args": { + "External id": 4720319,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[42076416, 1], [], [], []], "Input Dims": [[8, 42076416], [], [], []], "Ev Idx": 5974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358648828.591, "dur": 6005.251, + "args": { + "External id": 4720320,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[42076416, 1], [], [], []], "Input Dims": [[8, 42076416], [], [], []], "Ev Idx": 5975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358648851.376, "dur": 5.506, + "args": { + "External id": 4720321,"Record function id": 0, "Concrete Inputs": ["[4290]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358648863.993, "dur": 5928.537, + "args": { + "External id": 4720322,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[4290], [], [], [], [], [], [], []], "Ev Idx": 5977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358648866.694, "dur": 5925.152, + "args": { + "External id": 4720323,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[4290], [], [], [], [], [], []], "Ev Idx": 5978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358648874.478, "dur": 5.947, + "args": { + "External id": 4720324,"Record function id": 0, "Concrete Inputs": ["[4290]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358648884.184, "dur": 5904.733, + "args": { + "External id": 4720325,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4290], [4290], []], "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358655230.307, "dur": 45.608, + "args": { + "External id": 4720326,"Record function id": 0, "Ev Idx": 5981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 1336753, "tid": 1336753, + "ts": 1712358655277.316, "dur": 228.014, + "args": { + "External id": 4720327,"Record function id": 0, "Ev Idx": 5982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358655322.342, "dur": 172.967, + "args": { + "External id": 4720328,"Sequence number": 47018764, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "long int"], "Input Strides": [[2048, 1], [4096, 1]], "Input Dims": [[32000, 2048], [16, 4096]], "Ev Idx": 5983 + } + }, + { + "ph": "s", "id": 228, "pid": 1336753, "tid": 1336753, "ts": 1712358655322.342, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358655400.451, "dur": 55.386, + "args": { + "External id": 4720329,"kernel_hash": "cepuvqida76mp3inhfyv5xcp3dgr5kc6gyyaupvhufqptth43nyf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ep/cepuvqida76mp3inhfyv5xcp3dgr5kc6gyyaupvhufqptth43nyf.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096], [32000, 2048], [16, 4096, 2048], []], "Ev Idx": 5984 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358655568.328, "dur": 56.553, + "args": { + "External id": 4720330,"Record function id": 0, "Ev Idx": 5985 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1712358655636.791, "dur": 7556.162, + "args": { + "External id": 4720331,"Record function id": 0, "Ev Idx": 5986 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1712358655647.103, "dur": 1039.381, + "args": { + "External id": 4720332,"Record function id": 0, "Ev Idx": 5987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358655723.600, "dur": 12.217, + "args": { + "External id": 4720333,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358655750.408, "dur": 42.888, + "args": { + "External id": 4720334,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655759.509, "dur": 2.191, + "args": { + "External id": 4720335,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655763.277, "dur": 0.360, + "args": { + "External id": 4720336,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655764.321, "dur": 2.843, + "args": { + "External id": 4720337,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655770.596, "dur": 0.401, + "args": { + "External id": 4720338,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655771.742, "dur": 0.256, + "args": { + "External id": 4720339,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655777.362, "dur": 0.161, + "args": { + "External id": 4720340,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655778.144, "dur": 0.565, + "args": { + "External id": 4720341,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655779.306, "dur": 1.880, + "args": { + "External id": 4720342,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655786.171, "dur": 0.320, + "args": { + "External id": 4720343,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358655804.015, "dur": 36.142, + "args": { + "External id": 4720344,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358655872.521, "dur": 183.245, + "args": { + "External id": 4720345,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358655883.917, "dur": 4.394, + "args": { + "External id": 4720346,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358655893.529, "dur": 11.794, + "args": { + "External id": 4720347,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358655897.629, "dur": 7.295, + "args": { + "External id": 4720348,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655903.250, "dur": 0.558, + "args": { + "External id": 4720349,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358655911.744, "dur": 38.962, + "args": { + "External id": 4720350,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655913.173, "dur": 1.164, + "args": { + "External id": 4720351,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655919.048, "dur": 0.540, + "args": { + "External id": 4720352,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655923.201, "dur": 0.467, + "args": { + "External id": 4720353,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655927.621, "dur": 0.718, + "args": { + "External id": 4720354,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655929.558, "dur": 3.957, + "args": { + "External id": 4720355,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655934.681, "dur": 0.645, + "args": { + "External id": 4720356,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655939.084, "dur": 0.311, + "args": { + "External id": 4720357,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655942.853, "dur": 0.441, + "args": { + "External id": 4720358,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358655944.695, "dur": 0.529, + "args": { + "External id": 4720359,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358655966.266, "dur": 69.844, + "args": { + "External id": 4720360,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358656152.754, "dur": 377.813, + "args": { + "External id": 4720361,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358656194.277, "dur": 327.179, + "args": { + "External id": 4720362,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6017, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358656208.039, "dur": 303.060, + "args": { + "External id": 4720363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358656567.164, "dur": 4.514, + "args": { + "External id": 4720364,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6019, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1712358656721.436, "dur": 6074.215, + "args": { + "External id": 4720365,"Record function id": 0, "Ev Idx": 6020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656884.829, "dur": 9.418, + "args": { + "External id": 4720366,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656900.128, "dur": 1.738, + "args": { + "External id": 4720367,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656904.960, "dur": 1.591, + "args": { + "External id": 4720368,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656909.380, "dur": 3.660, + "args": { + "External id": 4720369,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656919.615, "dur": 1.475, + "args": { + "External id": 4720370,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656923.847, "dur": 1.048, + "args": { + "External id": 4720371,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656927.781, "dur": 1.467, + "args": { + "External id": 4720372,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656935.039, "dur": 2.740, + "args": { + "External id": 4720373,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656942.132, "dur": 1.304, + "args": { + "External id": 4720374,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358656945.783, "dur": 0.864, + "args": { + "External id": 4720375,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358656974.014, "dur": 5745.477, + "args": { + "External id": 4720376,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358657043.757, "dur": 5657.623, + "args": { + "External id": 4720377,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358657105.042, "dur": 21.721, + "args": { + "External id": 4720378,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358657133.041, "dur": 5509.999, + "args": { + "External id": 4720379,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358657139.142, "dur": 5502.709, + "args": { + "External id": 4720380,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358657147.035, "dur": 13.263, + "args": { + "External id": 4720381,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358657162.928, "dur": 5472.114, + "args": { + "External id": 4720382,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358663105.050, "dur": 47.406, + "args": { + "External id": 4720383,"Sequence number": 47018765, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6038 + } + }, + { + "ph": "s", "id": 227, "pid": 1336753, "tid": 1336753, "ts": 1712358663105.050, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358663129.019, "dur": 17.400, + "args": { + "External id": 4720384,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358663138.244, "dur": 7.607, + "args": { + "External id": 4720385,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358663247.832, "dur": 113.458, + "args": { + "External id": 4720386,"Record function id": 0, "Ev Idx": 6041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358663363.458, "dur": 1600.278, + "args": { + "External id": 4720387,"Record function id": 0, "Ev Idx": 6042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358663418.349, "dur": 1526.829, + "args": { + "External id": 4720388,"Sequence number": 47018766, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6043 + } + }, + { + "ph": "s", "id": 226, "pid": 1336753, "tid": 1336753, "ts": 1712358663418.349, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358663505.998, "dur": 62.642, + "args": { + "External id": 4720389,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358663586.121, "dur": 117.316, + "args": { + "External id": 4720390,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358663719.822, "dur": 52.065, + "args": { + "External id": 4720391,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358663782.533, "dur": 43.363, + "args": { + "External id": 4720392,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358663860.816, "dur": 37.113, + "args": { + "External id": 4720393,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358663926.755, "dur": 22.141, + "args": { + "External id": 4720394,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358663975.336, "dur": 288.218, + "args": { + "External id": 4720395,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358664146.715, "dur": 18.378, + "args": { + "External id": 4720396,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358664153.503, "dur": 10.062, + "args": { + "External id": 4720397,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358664168.370, "dur": 5.563, + "args": { + "External id": 4720398,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358664178.345, "dur": 1.331, + "args": { + "External id": 4720399,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358664182.892, "dur": 4.296, + "args": { + "External id": 4720400,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358664281.057, "dur": 85.352, + "args": { + "External id": 4720401,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358664417.001, "dur": 47.163, + "args": { + "External id": 4720402,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358664482.312, "dur": 73.223, + "args": { + "External id": 4720403,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358664571.006, "dur": 52.121, + "args": { + "External id": 4720404,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358664661.260, "dur": 48.947, + "args": { + "External id": 4720405,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358664719.475, "dur": 52.542, + "args": { + "External id": 4720406,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358664808.178, "dur": 32.465, + "args": { + "External id": 4720407,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6062 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1712358665174.020, "dur": 114.831, + "args": { + "External id": 4720408,"Record function id": 0, "Ev Idx": 6063 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358665389.325, "dur": 62.555, + "args": { + "External id": 4720409,"Record function id": 0, "Ev Idx": 6064 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1712358665464.669, "dur": 16955.986, + "args": { + "External id": 4720410,"Record function id": 0, "Ev Idx": 6065 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1712358665477.892, "dur": 1273.454, + "args": { + "External id": 4720411,"Record function id": 0, "Ev Idx": 6066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358665578.397, "dur": 12.573, + "args": { + "External id": 4720412,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358665608.016, "dur": 54.610, + "args": { + "External id": 4720413,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665616.843, "dur": 4.671, + "args": { + "External id": 4720414,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665624.220, "dur": 0.718, + "args": { + "External id": 4720415,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665628.605, "dur": 0.670, + "args": { + "External id": 4720416,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665632.721, "dur": 1.015, + "args": { + "External id": 4720417,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665635.104, "dur": 2.282, + "args": { + "External id": 4720418,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665641.135, "dur": 0.759, + "args": { + "External id": 4720419,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665645.369, "dur": 0.645, + "args": { + "External id": 4720420,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665647.365, "dur": 0.425, + "args": { + "External id": 4720421,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665651.577, "dur": 3.028, + "args": { + "External id": 4720422,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358665676.725, "dur": 57.787, + "args": { + "External id": 4720423,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358665776.705, "dur": 157.542, + "args": { + "External id": 4720424,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358665792.964, "dur": 5.801, + "args": { + "External id": 4720425,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358665805.729, "dur": 11.591, + "args": { + "External id": 4720426,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358665810.757, "dur": 5.997, + "args": { + "External id": 4720427,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665814.392, "dur": 0.864, + "args": { + "External id": 4720428,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358665826.835, "dur": 44.927, + "args": { + "External id": 4720429,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665830.998, "dur": 0.608, + "args": { + "External id": 4720430,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665833.270, "dur": 2.483, + "args": { + "External id": 4720431,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665837.575, "dur": 2.958, + "args": { + "External id": 4720432,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665844.564, "dur": 0.313, + "args": { + "External id": 4720433,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665846.326, "dur": 1.019, + "args": { + "External id": 4720434,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665851.062, "dur": 0.554, + "args": { + "External id": 4720435,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665856.801, "dur": 0.679, + "args": { + "External id": 4720436,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665858.786, "dur": 0.262, + "args": { + "External id": 4720437,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358665865.342, "dur": 0.287, + "args": { + "External id": 4720438,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358665888.652, "dur": 33.770, + "args": { + "External id": 4720439,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358666098.233, "dur": 524.326, + "args": { + "External id": 4720440,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358666140.416, "dur": 475.243, + "args": { + "External id": 4720441,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6096, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358666153.811, "dur": 454.041, + "args": { + "External id": 4720442,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358666652.373, "dur": 3.332, + "args": { + "External id": 4720443,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6098, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1712358666779.098, "dur": 15413.808, + "args": { + "External id": 4720444,"Record function id": 0, "Ev Idx": 6099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666915.672, "dur": 8.398, + "args": { + "External id": 4720445,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666928.897, "dur": 1.655, + "args": { + "External id": 4720446,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666933.203, "dur": 1.587, + "args": { + "External id": 4720447,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666937.543, "dur": 1.333, + "args": { + "External id": 4720448,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666941.005, "dur": 1.383, + "args": { + "External id": 4720449,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666947.047, "dur": 1.315, + "args": { + "External id": 4720450,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666953.322, "dur": 1.413, + "args": { + "External id": 4720451,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666957.153, "dur": 4.226, + "args": { + "External id": 4720452,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666963.865, "dur": 1.369, + "args": { + "External id": 4720453,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358666970.081, "dur": 0.838, + "args": { + "External id": 4720454,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358667056.024, "dur": 15071.639, + "args": { + "External id": 4720455,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358667117.217, "dur": 14997.906, + "args": { + "External id": 4720456,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358667149.474, "dur": 17.730, + "args": { + "External id": 4720457,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358667172.464, "dur": 14881.235, + "args": { + "External id": 4720458,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358667175.613, "dur": 14876.922, + "args": { + "External id": 4720459,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358667182.611, "dur": 7.142, + "args": { + "External id": 4720460,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358667192.211, "dur": 14854.808, + "args": { + "External id": 4720461,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358682358.675, "dur": 35.625, + "args": { + "External id": 4720462,"Sequence number": 47018767, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6117 + } + }, + { + "ph": "s", "id": 225, "pid": 1336753, "tid": 1336753, "ts": 1712358682358.675, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358682375.379, "dur": 14.208, + "args": { + "External id": 4720463,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358682382.885, "dur": 6.434, + "args": { + "External id": 4720464,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358682466.548, "dur": 80.766, + "args": { + "External id": 4720465,"Record function id": 0, "Ev Idx": 6120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358682548.849, "dur": 1112.984, + "args": { + "External id": 4720466,"Record function id": 0, "Ev Idx": 6121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358682590.912, "dur": 1057.740, + "args": { + "External id": 4720467,"Sequence number": 47018768, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6122 + } + }, + { + "ph": "s", "id": 224, "pid": 1336753, "tid": 1336753, "ts": 1712358682590.912, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358682674.115, "dur": 46.505, + "args": { + "External id": 4720468,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358682736.031, "dur": 102.010, + "args": { + "External id": 4720469,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358682846.634, "dur": 38.046, + "args": { + "External id": 4720470,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358682890.118, "dur": 30.748, + "args": { + "External id": 4720471,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358682953.772, "dur": 69.016, + "args": { + "External id": 4720472,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358683042.815, "dur": 35.150, + "args": { + "External id": 4720473,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358683097.476, "dur": 134.660, + "args": { + "External id": 4720474,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358683147.970, "dur": 13.398, + "args": { + "External id": 4720475,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358683152.785, "dur": 7.787, + "args": { + "External id": 4720476,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358683166.334, "dur": 6.126, + "args": { + "External id": 4720477,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358683173.550, "dur": 3.205, + "args": { + "External id": 4720478,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358683178.837, "dur": 2.802, + "args": { + "External id": 4720479,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358683242.909, "dur": 51.832, + "args": { + "External id": 4720480,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358683327.319, "dur": 29.129, + "args": { + "External id": 4720481,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358683366.015, "dur": 41.035, + "args": { + "External id": 4720482,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358683416.425, "dur": 34.690, + "args": { + "External id": 4720483,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358683475.286, "dur": 27.627, + "args": { + "External id": 4720484,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358683508.464, "dur": 33.681, + "args": { + "External id": 4720485,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358683561.576, "dur": 22.821, + "args": { + "External id": 4720486,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6141 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1712358683720.729, "dur": 79.203, + "args": { + "External id": 4720487,"Record function id": 0, "Ev Idx": 6142 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358683873.934, "dur": 45.566, + "args": { + "External id": 4720488,"Record function id": 0, "Ev Idx": 6143 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1712358683928.698, "dur": 18751.486, + "args": { + "External id": 4720489,"Record function id": 0, "Ev Idx": 6144 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1712358683941.553, "dur": 929.394, + "args": { + "External id": 4720490,"Record function id": 0, "Ev Idx": 6145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358684061.859, "dur": 23.891, + "args": { + "External id": 4720491,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358684103.818, "dur": 40.583, + "args": { + "External id": 4720492,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684108.567, "dur": 2.151, + "args": { + "External id": 4720493,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684115.305, "dur": 0.460, + "args": { + "External id": 4720494,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684118.764, "dur": 0.367, + "args": { + "External id": 4720495,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684119.958, "dur": 0.309, + "args": { + "External id": 4720496,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684123.121, "dur": 0.649, + "args": { + "External id": 4720497,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684126.986, "dur": 0.484, + "args": { + "External id": 4720498,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684128.164, "dur": 4.178, + "args": { + "External id": 4720499,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684135.215, "dur": 0.615, + "args": { + "External id": 4720500,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684136.462, "dur": 0.268, + "args": { + "External id": 4720501,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358684156.432, "dur": 45.173, + "args": { + "External id": 4720502,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358684238.477, "dur": 117.162, + "args": { + "External id": 4720503,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358684251.046, "dur": 3.941, + "args": { + "External id": 4720504,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358684260.209, "dur": 9.165, + "args": { + "External id": 4720505,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358684264.460, "dur": 4.491, + "args": { + "External id": 4720506,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684267.466, "dur": 0.451, + "args": { + "External id": 4720507,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358684275.958, "dur": 36.653, + "args": { + "External id": 4720508,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684279.721, "dur": 2.615, + "args": { + "External id": 4720509,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684283.376, "dur": 0.468, + "args": { + "External id": 4720510,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684284.553, "dur": 0.416, + "args": { + "External id": 4720511,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684290.124, "dur": 2.285, + "args": { + "External id": 4720512,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684293.082, "dur": 0.671, + "args": { + "External id": 4720513,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684296.835, "dur": 0.255, + "args": { + "External id": 4720514,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684300.082, "dur": 0.393, + "args": { + "External id": 4720515,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684301.313, "dur": 0.515, + "args": { + "External id": 4720516,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358684304.866, "dur": 2.769, + "args": { + "External id": 4720517,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358684322.320, "dur": 24.963, + "args": { + "External id": 4720518,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358684409.616, "dur": 360.774, + "args": { + "External id": 4720519,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358684443.701, "dur": 321.787, + "args": { + "External id": 4720520,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6175, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358684455.681, "dur": 303.503, + "args": { + "External id": 4720521,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358684799.861, "dur": 2.533, + "args": { + "External id": 4720522,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6177, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1712358684891.281, "dur": 17513.008, + "args": { + "External id": 4720523,"Record function id": 0, "Ev Idx": 6178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685025.230, "dur": 7.006, + "args": { + "External id": 4720524,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685036.508, "dur": 1.207, + "args": { + "External id": 4720525,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685039.491, "dur": 2.368, + "args": { + "External id": 4720526,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685043.726, "dur": 1.182, + "args": { + "External id": 4720527,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685046.646, "dur": 1.241, + "args": { + "External id": 4720528,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685049.335, "dur": 0.684, + "args": { + "External id": 4720529,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685054.004, "dur": 1.085, + "args": { + "External id": 4720530,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685056.839, "dur": 1.863, + "args": { + "External id": 4720531,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685060.084, "dur": 0.947, + "args": { + "External id": 4720532,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358685062.251, "dur": 0.697, + "args": { + "External id": 4720533,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358685101.069, "dur": 17230.254, + "args": { + "External id": 4720534,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358685117.084, "dur": 17200.220, + "args": { + "External id": 4720535,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358685142.065, "dur": 15.659, + "args": { + "External id": 4720536,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358685161.208, "dur": 17099.104, + "args": { + "External id": 4720537,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358685163.988, "dur": 17094.888, + "args": { + "External id": 4720538,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358685170.038, "dur": 5.314, + "args": { + "External id": 4720539,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358685177.054, "dur": 17075.161, + "args": { + "External id": 4720540,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358702602.312, "dur": 42.225, + "args": { + "External id": 4720541,"Sequence number": 47018769, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6196 + } + }, + { + "ph": "s", "id": 223, "pid": 1336753, "tid": 1336753, "ts": 1712358702602.312, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358702625.867, "dur": 12.807, + "args": { + "External id": 4720542,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358702631.436, "dur": 6.871, + "args": { + "External id": 4720543,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358702731.961, "dur": 99.075, + "args": { + "External id": 4720544,"Record function id": 0, "Ev Idx": 6199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358702833.385, "dur": 1674.790, + "args": { + "External id": 4720545,"Record function id": 0, "Ev Idx": 6200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358702884.490, "dur": 1605.170, + "args": { + "External id": 4720546,"Sequence number": 47018770, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6201 + } + }, + { + "ph": "s", "id": 222, "pid": 1336753, "tid": 1336753, "ts": 1712358702884.490, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358702974.360, "dur": 133.071, + "args": { + "External id": 4720547,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358703130.691, "dur": 113.789, + "args": { + "External id": 4720548,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358703258.568, "dur": 51.749, + "args": { + "External id": 4720549,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358703323.645, "dur": 43.613, + "args": { + "External id": 4720550,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358703407.123, "dur": 35.659, + "args": { + "External id": 4720551,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358703472.918, "dur": 24.309, + "args": { + "External id": 4720552,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358703523.979, "dur": 190.478, + "args": { + "External id": 4720553,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358703589.451, "dur": 16.745, + "args": { + "External id": 4720554,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358703596.543, "dur": 8.468, + "args": { + "External id": 4720555,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358703613.194, "dur": 9.869, + "args": { + "External id": 4720556,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358703625.016, "dur": 1.644, + "args": { + "External id": 4720557,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358703629.817, "dur": 6.635, + "args": { + "External id": 4720558,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358703733.241, "dur": 85.899, + "args": { + "External id": 4720559,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358703870.766, "dur": 46.923, + "args": { + "External id": 4720560,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358703932.308, "dur": 130.590, + "args": { + "External id": 4720561,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358704112.038, "dur": 65.336, + "args": { + "External id": 4720562,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358704211.940, "dur": 47.428, + "args": { + "External id": 4720563,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358704268.280, "dur": 52.818, + "args": { + "External id": 4720564,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358704351.533, "dur": 28.373, + "args": { + "External id": 4720565,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6220 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1712358704589.535, "dur": 109.438, + "args": { + "External id": 4720566,"Record function id": 0, "Ev Idx": 6221 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358704799.528, "dur": 65.820, + "args": { + "External id": 4720567,"Record function id": 0, "Ev Idx": 6222 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1712358704878.744, "dur": 17138.353, + "args": { + "External id": 4720568,"Record function id": 0, "Ev Idx": 6223 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1712358704895.262, "dur": 1476.872, + "args": { + "External id": 4720569,"Record function id": 0, "Ev Idx": 6224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358705057.424, "dur": 45.090, + "args": { + "External id": 4720570,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358705126.741, "dur": 97.741, + "args": { + "External id": 4720571,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705133.998, "dur": 2.516, + "args": { + "External id": 4720572,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705141.561, "dur": 0.389, + "args": { + "External id": 4720573,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705150.337, "dur": 0.470, + "args": { + "External id": 4720574,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705181.915, "dur": 0.743, + "args": { + "External id": 4720575,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705188.965, "dur": 0.416, + "args": { + "External id": 4720576,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705190.670, "dur": 0.567, + "args": { + "External id": 4720577,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705192.447, "dur": 4.265, + "args": { + "External id": 4720578,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705205.121, "dur": 1.203, + "args": { + "External id": 4720579,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705209.500, "dur": 1.057, + "args": { + "External id": 4720580,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358705241.122, "dur": 94.352, + "args": { + "External id": 4720581,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358705410.601, "dur": 225.256, + "args": { + "External id": 4720582,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358705430.644, "dur": 8.487, + "args": { + "External id": 4720583,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358705446.026, "dur": 13.210, + "args": { + "External id": 4720584,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358705451.466, "dur": 7.188, + "args": { + "External id": 4720585,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705455.899, "dur": 0.757, + "args": { + "External id": 4720586,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358705471.355, "dur": 46.943, + "args": { + "External id": 4720587,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705477.178, "dur": 2.737, + "args": { + "External id": 4720588,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705481.518, "dur": 0.496, + "args": { + "External id": 4720589,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705485.626, "dur": 0.414, + "args": { + "External id": 4720590,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705489.829, "dur": 1.978, + "args": { + "External id": 4720591,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705493.028, "dur": 0.435, + "args": { + "External id": 4720592,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705497.422, "dur": 0.596, + "args": { + "External id": 4720593,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705502.130, "dur": 0.589, + "args": { + "External id": 4720594,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705503.992, "dur": 0.491, + "args": { + "External id": 4720595,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358705508.441, "dur": 2.515, + "args": { + "External id": 4720596,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358705578.260, "dur": 45.018, + "args": { + "External id": 4720597,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358705715.588, "dur": 527.565, + "args": { + "External id": 4720598,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358705756.144, "dur": 480.588, + "args": { + "External id": 4720599,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6254, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358705771.770, "dur": 456.525, + "args": { + "External id": 4720600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358706276.091, "dur": 3.618, + "args": { + "External id": 4720601,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6256, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1712358706399.101, "dur": 15353.379, + "args": { + "External id": 4720602,"Record function id": 0, "Ev Idx": 6257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706528.912, "dur": 26.192, + "args": { + "External id": 4720603,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706578.604, "dur": 3.860, + "args": { + "External id": 4720604,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706585.461, "dur": 3.574, + "args": { + "External id": 4720605,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706592.483, "dur": 1.530, + "args": { + "External id": 4720606,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706596.121, "dur": 1.313, + "args": { + "External id": 4720607,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706599.667, "dur": 1.428, + "args": { + "External id": 4720608,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706606.142, "dur": 1.765, + "args": { + "External id": 4720609,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706611.670, "dur": 3.052, + "args": { + "External id": 4720610,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706617.241, "dur": 1.195, + "args": { + "External id": 4720611,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358706621.001, "dur": 1.200, + "args": { + "External id": 4720612,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358706650.151, "dur": 15038.831, + "args": { + "External id": 4720613,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358706670.672, "dur": 15006.097, + "args": { + "External id": 4720614,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358706701.758, "dur": 21.936, + "args": { + "External id": 4720615,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358706730.075, "dur": 14899.935, + "args": { + "External id": 4720616,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358706735.583, "dur": 14893.347, + "args": { + "External id": 4720617,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358706755.472, "dur": 29.533, + "args": { + "External id": 4720618,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358706791.558, "dur": 14831.484, + "args": { + "External id": 4720619,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358721914.406, "dur": 46.235, + "args": { + "External id": 4720620,"Sequence number": 47018771, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6275 + } + }, + { + "ph": "s", "id": 221, "pid": 1336753, "tid": 1336753, "ts": 1712358721914.406, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358721945.064, "dur": 10.976, + "args": { + "External id": 4720621,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358721949.714, "dur": 6.069, + "args": { + "External id": 4720622,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358722062.741, "dur": 91.236, + "args": { + "External id": 4720623,"Record function id": 0, "Ev Idx": 6278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358722156.496, "dur": 1229.732, + "args": { + "External id": 4720624,"Record function id": 0, "Ev Idx": 6279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358722201.702, "dur": 1170.115, + "args": { + "External id": 4720625,"Sequence number": 47018772, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6280 + } + }, + { + "ph": "s", "id": 220, "pid": 1336753, "tid": 1336753, "ts": 1712358722201.702, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358722275.494, "dur": 49.435, + "args": { + "External id": 4720626,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358722337.635, "dur": 114.014, + "args": { + "External id": 4720627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358722468.490, "dur": 41.955, + "args": { + "External id": 4720628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358722517.288, "dur": 30.860, + "args": { + "External id": 4720629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358722579.999, "dur": 31.106, + "args": { + "External id": 4720630,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358722628.716, "dur": 16.254, + "args": { + "External id": 4720631,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358722664.744, "dur": 133.008, + "args": { + "External id": 4720632,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358722715.634, "dur": 12.954, + "args": { + "External id": 4720633,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358722722.776, "dur": 5.061, + "args": { + "External id": 4720634,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358722730.862, "dur": 5.480, + "args": { + "External id": 4720635,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358722737.820, "dur": 1.047, + "args": { + "External id": 4720636,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358722743.142, "dur": 4.661, + "args": { + "External id": 4720637,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358722808.022, "dur": 44.387, + "args": { + "External id": 4720638,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358722883.595, "dur": 29.721, + "args": { + "External id": 4720639,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358722922.373, "dur": 39.424, + "args": { + "External id": 4720640,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358723107.749, "dur": 46.724, + "args": { + "External id": 4720641,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358723189.225, "dur": 30.600, + "args": { + "External id": 4720642,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358723226.557, "dur": 34.370, + "args": { + "External id": 4720643,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358723279.854, "dur": 23.018, + "args": { + "External id": 4720644,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1712358723449.880, "dur": 76.715, + "args": { + "External id": 4720645,"Record function id": 0, "Ev Idx": 6300 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358723602.088, "dur": 46.697, + "args": { + "External id": 4720646,"Record function id": 0, "Ev Idx": 6301 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1712358723658.613, "dur": 18687.860, + "args": { + "External id": 4720647,"Record function id": 0, "Ev Idx": 6302 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1712358723670.018, "dur": 895.948, + "args": { + "External id": 4720648,"Record function id": 0, "Ev Idx": 6303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358723749.938, "dur": 7.734, + "args": { + "External id": 4720649,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358723770.690, "dur": 38.685, + "args": { + "External id": 4720650,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723775.424, "dur": 1.965, + "args": { + "External id": 4720651,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723783.816, "dur": 0.441, + "args": { + "External id": 4720652,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723785.342, "dur": 0.411, + "args": { + "External id": 4720653,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723786.356, "dur": 0.400, + "args": { + "External id": 4720654,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723791.290, "dur": 0.474, + "args": { + "External id": 4720655,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723792.268, "dur": 0.393, + "args": { + "External id": 4720656,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723795.732, "dur": 4.057, + "args": { + "External id": 4720657,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723800.581, "dur": 0.438, + "args": { + "External id": 4720658,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723801.698, "dur": 0.931, + "args": { + "External id": 4720659,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358723823.418, "dur": 43.940, + "args": { + "External id": 4720660,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358723898.951, "dur": 162.474, + "args": { + "External id": 4720661,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358723911.910, "dur": 4.170, + "args": { + "External id": 4720662,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358723921.375, "dur": 9.398, + "args": { + "External id": 4720663,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358723925.703, "dur": 4.660, + "args": { + "External id": 4720664,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723928.690, "dur": 0.474, + "args": { + "External id": 4720665,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358723938.893, "dur": 31.490, + "args": { + "External id": 4720666,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723940.253, "dur": 2.790, + "args": { + "External id": 4720667,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723943.823, "dur": 0.433, + "args": { + "External id": 4720668,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723947.275, "dur": 0.381, + "args": { + "External id": 4720669,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723950.975, "dur": 2.206, + "args": { + "External id": 4720670,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723955.728, "dur": 0.474, + "args": { + "External id": 4720671,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723956.857, "dur": 0.357, + "args": { + "External id": 4720672,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723960.243, "dur": 0.372, + "args": { + "External id": 4720673,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723962.748, "dur": 0.534, + "args": { + "External id": 4720674,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358723963.783, "dur": 2.221, + "args": { + "External id": 4720675,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358724022.143, "dur": 29.561, + "args": { + "External id": 4720676,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358724133.191, "dur": 341.014, + "args": { + "External id": 4720677,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358724168.417, "dur": 301.039, + "args": { + "External id": 4720678,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6333, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358724181.094, "dur": 283.143, + "args": { + "External id": 4720679,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358724498.761, "dur": 2.139, + "args": { + "External id": 4720680,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6335, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1712358724586.311, "dur": 17546.895, + "args": { + "External id": 4720681,"Record function id": 0, "Ev Idx": 6336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724680.587, "dur": 6.475, + "args": { + "External id": 4720682,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724690.550, "dur": 1.311, + "args": { + "External id": 4720683,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724693.370, "dur": 3.022, + "args": { + "External id": 4720684,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724698.102, "dur": 0.968, + "args": { + "External id": 4720685,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724700.258, "dur": 0.951, + "args": { + "External id": 4720686,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724702.693, "dur": 0.960, + "args": { + "External id": 4720687,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724707.560, "dur": 1.113, + "args": { + "External id": 4720688,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724710.184, "dur": 2.407, + "args": { + "External id": 4720689,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724713.901, "dur": 0.709, + "args": { + "External id": 4720690,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358724715.900, "dur": 1.294, + "args": { + "External id": 4720691,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358724738.789, "dur": 17335.957, + "args": { + "External id": 4720692,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358724753.478, "dur": 17300.584, + "args": { + "External id": 4720693,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358724775.114, "dur": 13.800, + "args": { + "External id": 4720694,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358724791.855, "dur": 17220.353, + "args": { + "External id": 4720695,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358724794.333, "dur": 17216.916, + "args": { + "External id": 4720696,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358724802.236, "dur": 4.850, + "args": { + "External id": 4720697,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358724808.622, "dur": 17198.147, + "args": { + "External id": 4720698,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358742289.037, "dur": 31.326, + "args": { + "External id": 4720699,"Sequence number": 47018773, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6354 + } + }, + { + "ph": "s", "id": 219, "pid": 1336753, "tid": 1336753, "ts": 1712358742289.037, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358742305.196, "dur": 10.480, + "args": { + "External id": 4720700,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358742309.557, "dur": 5.891, + "args": { + "External id": 4720701,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358742388.575, "dur": 79.423, + "args": { + "External id": 4720702,"Record function id": 0, "Ev Idx": 6357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358742469.631, "dur": 1098.631, + "args": { + "External id": 4720703,"Record function id": 0, "Ev Idx": 6358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358742512.769, "dur": 1042.367, + "args": { + "External id": 4720704,"Sequence number": 47018774, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6359 + } + }, + { + "ph": "s", "id": 218, "pid": 1336753, "tid": 1336753, "ts": 1712358742512.769, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358742578.453, "dur": 44.128, + "args": { + "External id": 4720705,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358742635.847, "dur": 102.031, + "args": { + "External id": 4720706,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358742747.212, "dur": 37.332, + "args": { + "External id": 4720707,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358742794.907, "dur": 32.371, + "args": { + "External id": 4720708,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358742852.463, "dur": 27.243, + "args": { + "External id": 4720709,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358742897.431, "dur": 16.964, + "args": { + "External id": 4720710,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358742932.118, "dur": 191.698, + "args": { + "External id": 4720711,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358742978.911, "dur": 56.751, + "args": { + "External id": 4720712,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743028.115, "dur": 6.326, + "args": { + "External id": 4720713,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358743038.115, "dur": 6.322, + "args": { + "External id": 4720714,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358743045.470, "dur": 1.012, + "args": { + "External id": 4720715,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358743049.180, "dur": 4.205, + "args": { + "External id": 4720716,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358743136.381, "dur": 52.033, + "args": { + "External id": 4720717,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358743223.212, "dur": 30.110, + "args": { + "External id": 4720718,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358743262.115, "dur": 40.526, + "args": { + "External id": 4720719,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358743310.399, "dur": 34.433, + "args": { + "External id": 4720720,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358743368.868, "dur": 29.821, + "args": { + "External id": 4720721,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358743404.626, "dur": 32.678, + "args": { + "External id": 4720722,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358743459.467, "dur": 18.576, + "args": { + "External id": 4720723,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6378 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1712358743631.152, "dur": 75.591, + "args": { + "External id": 4720724,"Record function id": 0, "Ev Idx": 6379 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358743781.230, "dur": 48.828, + "args": { + "External id": 4720725,"Record function id": 0, "Ev Idx": 6380 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1712358743839.315, "dur": 18501.477, + "args": { + "External id": 4720726,"Record function id": 0, "Ev Idx": 6381 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1712358743850.327, "dur": 957.369, + "args": { + "External id": 4720727,"Record function id": 0, "Ev Idx": 6382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358743928.483, "dur": 7.114, + "args": { + "External id": 4720728,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358743948.694, "dur": 94.257, + "args": { + "External id": 4720729,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743953.823, "dur": 1.995, + "args": { + "External id": 4720730,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743961.701, "dur": 0.668, + "args": { + "External id": 4720731,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743963.324, "dur": 0.409, + "args": { + "External id": 4720732,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743966.481, "dur": 0.403, + "args": { + "External id": 4720733,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743970.172, "dur": 0.535, + "args": { + "External id": 4720734,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743971.545, "dur": 0.453, + "args": { + "External id": 4720735,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743974.022, "dur": 4.179, + "args": { + "External id": 4720736,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743978.948, "dur": 0.321, + "args": { + "External id": 4720737,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358743980.064, "dur": 0.436, + "args": { + "External id": 4720738,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358744060.271, "dur": 61.991, + "args": { + "External id": 4720739,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358744161.002, "dur": 130.334, + "args": { + "External id": 4720740,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358744175.545, "dur": 5.466, + "args": { + "External id": 4720741,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358744186.725, "dur": 12.704, + "args": { + "External id": 4720742,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358744191.402, "dur": 7.618, + "args": { + "External id": 4720743,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744196.750, "dur": 0.867, + "args": { + "External id": 4720744,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358744207.021, "dur": 34.617, + "args": { + "External id": 4720745,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744209.164, "dur": 2.469, + "args": { + "External id": 4720746,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744215.148, "dur": 0.370, + "args": { + "External id": 4720747,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744216.445, "dur": 0.444, + "args": { + "External id": 4720748,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744220.362, "dur": 2.547, + "args": { + "External id": 4720749,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744225.656, "dur": 0.326, + "args": { + "External id": 4720750,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744226.876, "dur": 0.340, + "args": { + "External id": 4720751,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744228.682, "dur": 0.527, + "args": { + "External id": 4720752,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744232.789, "dur": 0.356, + "args": { + "External id": 4720753,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358744234.235, "dur": 2.717, + "args": { + "External id": 4720754,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358744258.493, "dur": 24.398, + "args": { + "External id": 4720755,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358744348.229, "dur": 362.803, + "args": { + "External id": 4720756,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358744382.740, "dur": 322.813, + "args": { + "External id": 4720757,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6412, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358744393.965, "dur": 303.491, + "args": { + "External id": 4720758,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358744736.851, "dur": 2.399, + "args": { + "External id": 4720759,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6414, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1712358744827.244, "dur": 17307.597, + "args": { + "External id": 4720760,"Record function id": 0, "Ev Idx": 6415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744926.650, "dur": 6.107, + "args": { + "External id": 4720761,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744936.222, "dur": 1.283, + "args": { + "External id": 4720762,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744939.543, "dur": 3.088, + "args": { + "External id": 4720763,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744944.493, "dur": 0.976, + "args": { + "External id": 4720764,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744947.249, "dur": 1.052, + "args": { + "External id": 4720765,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744949.692, "dur": 0.789, + "args": { + "External id": 4720766,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744954.360, "dur": 0.838, + "args": { + "External id": 4720767,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744956.700, "dur": 3.011, + "args": { + "External id": 4720768,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744961.275, "dur": 0.684, + "args": { + "External id": 4720769,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358744965.109, "dur": 0.777, + "args": { + "External id": 4720770,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358745024.189, "dur": 17060.894, + "args": { + "External id": 4720771,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358745049.166, "dur": 17026.770, + "args": { + "External id": 4720772,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358745085.362, "dur": 15.731, + "args": { + "External id": 4720773,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358745104.235, "dur": 16924.622, + "args": { + "External id": 4720774,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358745106.677, "dur": 16921.389, + "args": { + "External id": 4720775,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358745114.419, "dur": 5.412, + "args": { + "External id": 4720776,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358745121.544, "dur": 16903.444, + "args": { + "External id": 4720777,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358762286.435, "dur": 28.713, + "args": { + "External id": 4720778,"Sequence number": 47018775, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6433 + } + }, + { + "ph": "s", "id": 217, "pid": 1336753, "tid": 1336753, "ts": 1712358762286.435, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358762301.568, "dur": 8.899, + "args": { + "External id": 4720779,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358762304.986, "dur": 5.253, + "args": { + "External id": 4720780,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358762381.913, "dur": 75.464, + "args": { + "External id": 4720781,"Record function id": 0, "Ev Idx": 6436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358762461.581, "dur": 1131.922, + "args": { + "External id": 4720782,"Record function id": 0, "Ev Idx": 6437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358762506.638, "dur": 1072.963, + "args": { + "External id": 4720783,"Sequence number": 47018776, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6438 + } + }, + { + "ph": "s", "id": 216, "pid": 1336753, "tid": 1336753, "ts": 1712358762506.638, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358762571.617, "dur": 45.421, + "args": { + "External id": 4720784,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358762629.936, "dur": 99.997, + "args": { + "External id": 4720785,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358762741.592, "dur": 38.943, + "args": { + "External id": 4720786,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358762788.544, "dur": 30.028, + "args": { + "External id": 4720787,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358762841.645, "dur": 29.046, + "args": { + "External id": 4720788,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358762889.354, "dur": 17.904, + "args": { + "External id": 4720789,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358762937.806, "dur": 206.797, + "args": { + "External id": 4720790,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358763028.663, "dur": 11.486, + "args": { + "External id": 4720791,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358763033.436, "dur": 5.839, + "args": { + "External id": 4720792,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358763042.421, "dur": 4.871, + "args": { + "External id": 4720793,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358763048.348, "dur": 0.951, + "args": { + "External id": 4720794,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358763051.658, "dur": 5.615, + "args": { + "External id": 4720795,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358763160.934, "dur": 59.867, + "args": { + "External id": 4720796,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358763257.433, "dur": 32.331, + "args": { + "External id": 4720797,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358763299.369, "dur": 39.144, + "args": { + "External id": 4720798,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358763348.321, "dur": 33.724, + "args": { + "External id": 4720799,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358763401.454, "dur": 25.663, + "args": { + "External id": 4720800,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358763432.613, "dur": 32.318, + "args": { + "External id": 4720801,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358763485.558, "dur": 23.162, + "args": { + "External id": 4720802,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1712358763655.168, "dur": 75.541, + "args": { + "External id": 4720803,"Record function id": 0, "Ev Idx": 6458 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358763803.558, "dur": 47.570, + "args": { + "External id": 4720804,"Record function id": 0, "Ev Idx": 6459 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1712358763860.608, "dur": 18094.577, + "args": { + "External id": 4720805,"Record function id": 0, "Ev Idx": 6460 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1712358763871.496, "dur": 973.273, + "args": { + "External id": 4720806,"Record function id": 0, "Ev Idx": 6461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358763950.576, "dur": 7.123, + "args": { + "External id": 4720807,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358763970.919, "dur": 85.700, + "args": { + "External id": 4720808,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358763975.777, "dur": 2.006, + "args": { + "External id": 4720809,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764025.653, "dur": 0.960, + "args": { + "External id": 4720810,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764030.119, "dur": 0.545, + "args": { + "External id": 4720811,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764032.641, "dur": 0.692, + "args": { + "External id": 4720812,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764036.636, "dur": 0.421, + "args": { + "External id": 4720813,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764038.419, "dur": 0.381, + "args": { + "External id": 4720814,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764040.735, "dur": 4.391, + "args": { + "External id": 4720815,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764046.888, "dur": 0.443, + "args": { + "External id": 4720816,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764049.530, "dur": 0.331, + "args": { + "External id": 4720817,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358764084.077, "dur": 45.449, + "args": { + "External id": 4720818,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358764168.735, "dur": 123.692, + "args": { + "External id": 4720819,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358764183.340, "dur": 5.306, + "args": { + "External id": 4720820,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358764194.105, "dur": 10.718, + "args": { + "External id": 4720821,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358764198.161, "dur": 6.273, + "args": { + "External id": 4720822,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764202.471, "dur": 0.540, + "args": { + "External id": 4720823,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358764212.416, "dur": 36.222, + "args": { + "External id": 4720824,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764214.956, "dur": 3.067, + "args": { + "External id": 4720825,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764219.983, "dur": 0.644, + "args": { + "External id": 4720826,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764222.587, "dur": 0.318, + "args": { + "External id": 4720827,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764226.717, "dur": 2.325, + "args": { + "External id": 4720828,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764230.540, "dur": 0.326, + "args": { + "External id": 4720829,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764232.662, "dur": 0.350, + "args": { + "External id": 4720830,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764236.870, "dur": 0.306, + "args": { + "External id": 4720831,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764238.708, "dur": 0.478, + "args": { + "External id": 4720832,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358764241.025, "dur": 2.506, + "args": { + "External id": 4720833,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358764260.942, "dur": 23.548, + "args": { + "External id": 4720834,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358764346.844, "dur": 394.969, + "args": { + "External id": 4720835,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358764381.293, "dur": 354.605, + "args": { + "External id": 4720836,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6491, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358764393.019, "dur": 336.294, + "args": { + "External id": 4720837,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358764769.936, "dur": 2.488, + "args": { + "External id": 4720838,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6493, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1712358764868.084, "dur": 16892.990, + "args": { + "External id": 4720839,"Record function id": 0, "Ev Idx": 6494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358764963.882, "dur": 6.226, + "args": { + "External id": 4720840,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358764974.344, "dur": 1.602, + "args": { + "External id": 4720841,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358764977.924, "dur": 2.820, + "args": { + "External id": 4720842,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358765034.807, "dur": 1.772, + "args": { + "External id": 4720843,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358765039.523, "dur": 1.096, + "args": { + "External id": 4720844,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358765042.517, "dur": 1.114, + "args": { + "External id": 4720845,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358765047.565, "dur": 0.878, + "args": { + "External id": 4720846,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358765050.432, "dur": 2.554, + "args": { + "External id": 4720847,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358765054.569, "dur": 1.158, + "args": { + "External id": 4720848,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358765057.642, "dur": 0.722, + "args": { + "External id": 4720849,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358765094.933, "dur": 16619.645, + "args": { + "External id": 4720850,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358765111.357, "dur": 16596.428, + "args": { + "External id": 4720851,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358765136.766, "dur": 14.819, + "args": { + "External id": 4720852,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358765154.668, "dur": 16520.109, + "args": { + "External id": 4720853,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358765157.248, "dur": 16517.049, + "args": { + "External id": 4720854,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358765164.261, "dur": 5.138, + "args": { + "External id": 4720855,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358765171.076, "dur": 16500.606, + "args": { + "External id": 4720856,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358781903.751, "dur": 27.021, + "args": { + "External id": 4720857,"Sequence number": 47018777, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6512 + } + }, + { + "ph": "s", "id": 215, "pid": 1336753, "tid": 1336753, "ts": 1712358781903.751, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358781919.201, "dur": 7.024, + "args": { + "External id": 4720858,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358781922.206, "dur": 3.826, + "args": { + "External id": 4720859,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358782024.754, "dur": 90.656, + "args": { + "External id": 4720860,"Record function id": 0, "Ev Idx": 6515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358782118.413, "dur": 1088.767, + "args": { + "External id": 4720861,"Record function id": 0, "Ev Idx": 6516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358782162.927, "dur": 1030.763, + "args": { + "External id": 4720862,"Sequence number": 47018778, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6517 + } + }, + { + "ph": "s", "id": 214, "pid": 1336753, "tid": 1336753, "ts": 1712358782162.927, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358782229.435, "dur": 45.401, + "args": { + "External id": 4720863,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358782287.360, "dur": 102.850, + "args": { + "External id": 4720864,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358782400.304, "dur": 37.866, + "args": { + "External id": 4720865,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358782446.644, "dur": 30.437, + "args": { + "External id": 4720866,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358782501.590, "dur": 25.692, + "args": { + "External id": 4720867,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358782544.895, "dur": 16.834, + "args": { + "External id": 4720868,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358782581.191, "dur": 125.179, + "args": { + "External id": 4720869,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358782628.014, "dur": 11.465, + "args": { + "External id": 4720870,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358782632.673, "dur": 6.087, + "args": { + "External id": 4720871,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358782642.361, "dur": 5.446, + "args": { + "External id": 4720872,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358782649.083, "dur": 0.868, + "args": { + "External id": 4720873,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358782652.496, "dur": 3.921, + "args": { + "External id": 4720874,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358782717.260, "dur": 45.517, + "args": { + "External id": 4720875,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358782793.983, "dur": 31.968, + "args": { + "External id": 4720876,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358782834.981, "dur": 40.107, + "args": { + "External id": 4720877,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358782882.974, "dur": 34.643, + "args": { + "External id": 4720878,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358782940.955, "dur": 29.641, + "args": { + "External id": 4720879,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358782976.493, "dur": 77.569, + "args": { + "External id": 4720880,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358783093.821, "dur": 22.485, + "args": { + "External id": 4720881,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1712358783270.104, "dur": 75.255, + "args": { + "External id": 4720882,"Record function id": 0, "Ev Idx": 6537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358783423.761, "dur": 48.081, + "args": { + "External id": 4720883,"Record function id": 0, "Ev Idx": 6538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1712358783481.837, "dur": 18053.409, + "args": { + "External id": 4720884,"Record function id": 0, "Ev Idx": 6539 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1712358783490.829, "dur": 910.426, + "args": { + "External id": 4720885,"Record function id": 0, "Ev Idx": 6540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358783570.893, "dur": 8.154, + "args": { + "External id": 4720886,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358783592.929, "dur": 43.121, + "args": { + "External id": 4720887,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783598.516, "dur": 1.975, + "args": { + "External id": 4720888,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783605.842, "dur": 0.373, + "args": { + "External id": 4720889,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783608.164, "dur": 0.739, + "args": { + "External id": 4720890,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783610.342, "dur": 0.527, + "args": { + "External id": 4720891,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783614.806, "dur": 0.523, + "args": { + "External id": 4720892,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783617.030, "dur": 0.465, + "args": { + "External id": 4720893,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783618.848, "dur": 4.216, + "args": { + "External id": 4720894,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783624.835, "dur": 0.386, + "args": { + "External id": 4720895,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783627.152, "dur": 0.370, + "args": { + "External id": 4720896,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358783649.638, "dur": 38.889, + "args": { + "External id": 4720897,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358783721.289, "dur": 121.841, + "args": { + "External id": 4720898,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358783734.006, "dur": 3.522, + "args": { + "External id": 4720899,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358783742.456, "dur": 10.472, + "args": { + "External id": 4720900,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358783746.928, "dur": 5.565, + "args": { + "External id": 4720901,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783750.602, "dur": 0.587, + "args": { + "External id": 4720902,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358783759.659, "dur": 36.608, + "args": { + "External id": 4720903,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783762.019, "dur": 2.575, + "args": { + "External id": 4720904,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783766.432, "dur": 0.405, + "args": { + "External id": 4720905,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783768.721, "dur": 0.678, + "args": { + "External id": 4720906,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783773.416, "dur": 2.418, + "args": { + "External id": 4720907,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783777.414, "dur": 0.389, + "args": { + "External id": 4720908,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783779.312, "dur": 0.547, + "args": { + "External id": 4720909,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783782.224, "dur": 0.635, + "args": { + "External id": 4720910,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783784.970, "dur": 0.468, + "args": { + "External id": 4720911,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358783787.025, "dur": 2.344, + "args": { + "External id": 4720912,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358783809.460, "dur": 24.842, + "args": { + "External id": 4720913,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358783894.020, "dur": 405.117, + "args": { + "External id": 4720914,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358783928.126, "dur": 365.007, + "args": { + "External id": 4720915,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6570, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358783940.018, "dur": 346.484, + "args": { + "External id": 4720916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358784329.215, "dur": 2.749, + "args": { + "External id": 4720917,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6572, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1712358784421.630, "dur": 16920.636, + "args": { + "External id": 4720918,"Record function id": 0, "Ev Idx": 6573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784526.527, "dur": 6.460, + "args": { + "External id": 4720919,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784536.685, "dur": 1.518, + "args": { + "External id": 4720920,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784540.311, "dur": 2.901, + "args": { + "External id": 4720921,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784547.231, "dur": 1.165, + "args": { + "External id": 4720922,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784550.089, "dur": 1.506, + "args": { + "External id": 4720923,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784553.382, "dur": 1.474, + "args": { + "External id": 4720924,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784556.755, "dur": 1.406, + "args": { + "External id": 4720925,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784562.566, "dur": 3.668, + "args": { + "External id": 4720926,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784567.748, "dur": 1.599, + "args": { + "External id": 4720927,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358784571.027, "dur": 1.027, + "args": { + "External id": 4720928,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358784591.147, "dur": 16704.201, + "args": { + "External id": 4720929,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358784606.543, "dur": 16681.982, + "args": { + "External id": 4720930,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358784625.898, "dur": 13.192, + "args": { + "External id": 4720931,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358784644.273, "dur": 16610.846, + "args": { + "External id": 4720932,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358784646.733, "dur": 16607.806, + "args": { + "External id": 4720933,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358784653.228, "dur": 4.610, + "args": { + "External id": 4720934,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358784659.488, "dur": 16592.233, + "args": { + "External id": 4720935,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358801481.929, "dur": 28.742, + "args": { + "External id": 4720936,"Sequence number": 47018779, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6591 + } + }, + { + "ph": "s", "id": 213, "pid": 1336753, "tid": 1336753, "ts": 1712358801481.929, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358801498.757, "dur": 7.609, + "args": { + "External id": 4720937,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358801502.194, "dur": 3.979, + "args": { + "External id": 4720938,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358801573.867, "dur": 75.481, + "args": { + "External id": 4720939,"Record function id": 0, "Ev Idx": 6594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358801651.838, "dur": 1084.385, + "args": { + "External id": 4720940,"Record function id": 0, "Ev Idx": 6595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358801693.115, "dur": 1030.326, + "args": { + "External id": 4720941,"Sequence number": 47018780, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6596 + } + }, + { + "ph": "s", "id": 212, "pid": 1336753, "tid": 1336753, "ts": 1712358801693.115, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358801758.295, "dur": 42.506, + "args": { + "External id": 4720942,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358801813.336, "dur": 99.785, + "args": { + "External id": 4720943,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358801922.587, "dur": 37.578, + "args": { + "External id": 4720944,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358801969.885, "dur": 73.984, + "args": { + "External id": 4720945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358802088.264, "dur": 31.372, + "args": { + "External id": 4720946,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358802138.566, "dur": 15.274, + "args": { + "External id": 4720947,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358802174.322, "dur": 135.686, + "args": { + "External id": 4720948,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358802222.379, "dur": 11.546, + "args": { + "External id": 4720949,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358802227.757, "dur": 5.387, + "args": { + "External id": 4720950,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358802236.609, "dur": 5.850, + "args": { + "External id": 4720951,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358802252.164, "dur": 0.968, + "args": { + "External id": 4720952,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358802255.670, "dur": 3.837, + "args": { + "External id": 4720953,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358802321.271, "dur": 50.860, + "args": { + "External id": 4720954,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358802402.934, "dur": 28.509, + "args": { + "External id": 4720955,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358802440.549, "dur": 39.905, + "args": { + "External id": 4720956,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358802487.639, "dur": 34.068, + "args": { + "External id": 4720957,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358802544.103, "dur": 28.525, + "args": { + "External id": 4720958,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358802577.899, "dur": 33.196, + "args": { + "External id": 4720959,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358802633.205, "dur": 19.840, + "args": { + "External id": 4720960,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6615 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1712358802797.068, "dur": 77.145, + "args": { + "External id": 4720961,"Record function id": 0, "Ev Idx": 6616 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358802948.903, "dur": 91.634, + "args": { + "External id": 4720962,"Record function id": 0, "Ev Idx": 6617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1712358803051.520, "dur": 18309.783, + "args": { + "External id": 4720963,"Record function id": 0, "Ev Idx": 6618 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1712358803061.648, "dur": 883.918, + "args": { + "External id": 4720964,"Record function id": 0, "Ev Idx": 6619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358803159.995, "dur": 8.372, + "args": { + "External id": 4720965,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358803183.384, "dur": 42.611, + "args": { + "External id": 4720966,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803189.078, "dur": 2.002, + "args": { + "External id": 4720967,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803195.819, "dur": 0.618, + "args": { + "External id": 4720968,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803198.252, "dur": 0.362, + "args": { + "External id": 4720969,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803199.925, "dur": 0.734, + "args": { + "External id": 4720970,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803203.904, "dur": 0.611, + "args": { + "External id": 4720971,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803205.950, "dur": 0.460, + "args": { + "External id": 4720972,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803207.772, "dur": 4.150, + "args": { + "External id": 4720973,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803213.286, "dur": 0.306, + "args": { + "External id": 4720974,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803215.675, "dur": 0.375, + "args": { + "External id": 4720975,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358803239.073, "dur": 44.097, + "args": { + "External id": 4720976,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358803317.191, "dur": 115.360, + "args": { + "External id": 4720977,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358803329.997, "dur": 4.110, + "args": { + "External id": 4720978,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358803339.194, "dur": 10.367, + "args": { + "External id": 4720979,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358803343.663, "dur": 5.504, + "args": { + "External id": 4720980,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803347.117, "dur": 0.788, + "args": { + "External id": 4720981,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358803356.300, "dur": 33.987, + "args": { + "External id": 4720982,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803358.418, "dur": 3.060, + "args": { + "External id": 4720983,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803363.070, "dur": 0.524, + "args": { + "External id": 4720984,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803365.086, "dur": 0.285, + "args": { + "External id": 4720985,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803369.168, "dur": 2.201, + "args": { + "External id": 4720986,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803372.601, "dur": 0.239, + "args": { + "External id": 4720987,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803374.159, "dur": 0.332, + "args": { + "External id": 4720988,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803377.934, "dur": 0.591, + "args": { + "External id": 4720989,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803379.797, "dur": 0.593, + "args": { + "External id": 4720990,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358803381.672, "dur": 2.309, + "args": { + "External id": 4720991,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358803400.225, "dur": 23.899, + "args": { + "External id": 4720992,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358803482.218, "dur": 367.607, + "args": { + "External id": 4720993,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358803513.353, "dur": 331.507, + "args": { + "External id": 4720994,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6649, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358803524.415, "dur": 314.570, + "args": { + "External id": 4720995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358803876.031, "dur": 2.555, + "args": { + "External id": 4720996,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6651, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1712358803963.754, "dur": 17190.320, + "args": { + "External id": 4720997,"Record function id": 0, "Ev Idx": 6652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804129.354, "dur": 6.753, + "args": { + "External id": 4720998,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804140.533, "dur": 1.471, + "args": { + "External id": 4720999,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804143.879, "dur": 3.337, + "args": { + "External id": 4721000,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804149.155, "dur": 0.956, + "args": { + "External id": 4721001,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804151.660, "dur": 1.058, + "args": { + "External id": 4721002,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804154.229, "dur": 1.117, + "args": { + "External id": 4721003,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804159.415, "dur": 1.166, + "args": { + "External id": 4721004,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804162.289, "dur": 3.300, + "args": { + "External id": 4721005,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804167.276, "dur": 0.938, + "args": { + "External id": 4721006,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358804169.688, "dur": 1.227, + "args": { + "External id": 4721007,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358804217.809, "dur": 16880.941, + "args": { + "External id": 4721008,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358804237.119, "dur": 16853.637, + "args": { + "External id": 4721009,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358804257.451, "dur": 14.533, + "args": { + "External id": 4721010,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358804274.922, "dur": 16768.301, + "args": { + "External id": 4721011,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358804277.518, "dur": 16764.674, + "args": { + "External id": 4721012,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358804283.941, "dur": 4.975, + "args": { + "External id": 4721013,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358804290.635, "dur": 16748.031, + "args": { + "External id": 4721014,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358821306.457, "dur": 30.053, + "args": { + "External id": 4721015,"Sequence number": 47018781, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6670 + } + }, + { + "ph": "s", "id": 211, "pid": 1336753, "tid": 1336753, "ts": 1712358821306.457, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358821322.634, "dur": 9.227, + "args": { + "External id": 4721016,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358821326.566, "dur": 5.036, + "args": { + "External id": 4721017,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358821403.858, "dur": 73.001, + "args": { + "External id": 4721018,"Record function id": 0, "Ev Idx": 6673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358821478.417, "dur": 1076.777, + "args": { + "External id": 4721019,"Record function id": 0, "Ev Idx": 6674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358821519.726, "dur": 1022.089, + "args": { + "External id": 4721020,"Sequence number": 47018782, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6675 + } + }, + { + "ph": "s", "id": 210, "pid": 1336753, "tid": 1336753, "ts": 1712358821519.726, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358821584.925, "dur": 40.891, + "args": { + "External id": 4721021,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358821638.424, "dur": 102.368, + "args": { + "External id": 4721022,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358821752.547, "dur": 37.435, + "args": { + "External id": 4721023,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358821797.976, "dur": 31.041, + "args": { + "External id": 4721024,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358821853.307, "dur": 27.363, + "args": { + "External id": 4721025,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358821899.490, "dur": 15.457, + "args": { + "External id": 4721026,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358821934.050, "dur": 183.420, + "args": { + "External id": 4721027,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358821980.290, "dur": 50.821, + "args": { + "External id": 4721028,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822023.713, "dur": 6.511, + "args": { + "External id": 4721029,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358822033.656, "dur": 5.257, + "args": { + "External id": 4721030,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358822040.189, "dur": 1.248, + "args": { + "External id": 4721031,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358822044.206, "dur": 4.256, + "args": { + "External id": 4721032,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358822129.656, "dur": 51.128, + "args": { + "External id": 4721033,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358822214.441, "dur": 29.806, + "args": { + "External id": 4721034,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358822254.434, "dur": 40.956, + "args": { + "External id": 4721035,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358822302.998, "dur": 33.661, + "args": { + "External id": 4721036,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358822360.327, "dur": 27.855, + "args": { + "External id": 4721037,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358822394.349, "dur": 34.354, + "args": { + "External id": 4721038,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358822448.449, "dur": 20.262, + "args": { + "External id": 4721039,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6694 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1712358822617.877, "dur": 74.156, + "args": { + "External id": 4721040,"Record function id": 0, "Ev Idx": 6695 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358822768.040, "dur": 46.259, + "args": { + "External id": 4721041,"Record function id": 0, "Ev Idx": 6696 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1712358822823.370, "dur": 18321.173, + "args": { + "External id": 4721042,"Record function id": 0, "Ev Idx": 6697 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1712358822830.588, "dur": 924.303, + "args": { + "External id": 4721043,"Record function id": 0, "Ev Idx": 6698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358822908.602, "dur": 7.110, + "args": { + "External id": 4721044,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358822929.388, "dur": 39.838, + "args": { + "External id": 4721045,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822934.798, "dur": 2.136, + "args": { + "External id": 4721046,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822941.079, "dur": 0.555, + "args": { + "External id": 4721047,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822943.040, "dur": 0.462, + "args": { + "External id": 4721048,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822945.018, "dur": 0.414, + "args": { + "External id": 4721049,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822948.979, "dur": 0.378, + "args": { + "External id": 4721050,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822950.415, "dur": 0.748, + "args": { + "External id": 4721051,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822952.391, "dur": 4.589, + "args": { + "External id": 4721052,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822958.300, "dur": 0.622, + "args": { + "External id": 4721053,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358822960.431, "dur": 0.683, + "args": { + "External id": 4721054,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358822980.947, "dur": 97.184, + "args": { + "External id": 4721055,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358823116.782, "dur": 163.924, + "args": { + "External id": 4721056,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358823130.974, "dur": 5.541, + "args": { + "External id": 4721057,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358823141.774, "dur": 10.597, + "args": { + "External id": 4721058,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358823145.954, "dur": 5.997, + "args": { + "External id": 4721059,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823149.643, "dur": 0.722, + "args": { + "External id": 4721060,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358823159.580, "dur": 35.601, + "args": { + "External id": 4721061,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823161.530, "dur": 2.861, + "args": { + "External id": 4721062,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823169.144, "dur": 0.678, + "args": { + "External id": 4721063,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823171.369, "dur": 0.609, + "args": { + "External id": 4721064,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823175.140, "dur": 2.239, + "args": { + "External id": 4721065,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823178.578, "dur": 0.504, + "args": { + "External id": 4721066,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823180.127, "dur": 2.250, + "args": { + "External id": 4721067,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823183.586, "dur": 0.534, + "args": { + "External id": 4721068,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823185.154, "dur": 0.522, + "args": { + "External id": 4721069,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358823189.152, "dur": 0.562, + "args": { + "External id": 4721070,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358823244.314, "dur": 27.724, + "args": { + "External id": 4721071,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358823335.903, "dur": 332.156, + "args": { + "External id": 4721072,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358823371.279, "dur": 292.420, + "args": { + "External id": 4721073,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6728, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358823382.683, "dur": 275.495, + "args": { + "External id": 4721074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358823690.713, "dur": 2.192, + "args": { + "External id": 4721075,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6730, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1712358823773.700, "dur": 17136.100, + "args": { + "External id": 4721076,"Record function id": 0, "Ev Idx": 6731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823864.321, "dur": 5.549, + "args": { + "External id": 4721077,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823873.848, "dur": 1.256, + "args": { + "External id": 4721078,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823877.173, "dur": 3.475, + "args": { + "External id": 4721079,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823882.702, "dur": 0.909, + "args": { + "External id": 4721080,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823885.317, "dur": 0.789, + "args": { + "External id": 4721081,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823887.743, "dur": 0.878, + "args": { + "External id": 4721082,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823892.364, "dur": 1.104, + "args": { + "External id": 4721083,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823894.977, "dur": 2.645, + "args": { + "External id": 4721084,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823899.025, "dur": 1.332, + "args": { + "External id": 4721085,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358823901.790, "dur": 1.002, + "args": { + "External id": 4721086,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358823922.244, "dur": 16942.008, + "args": { + "External id": 4721087,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358823937.697, "dur": 16919.885, + "args": { + "External id": 4721088,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358823957.856, "dur": 13.684, + "args": { + "External id": 4721089,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358823974.253, "dur": 16849.829, + "args": { + "External id": 4721090,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358823976.836, "dur": 16846.627, + "args": { + "External id": 4721091,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358824022.727, "dur": 7.474, + "args": { + "External id": 4721092,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358824032.136, "dur": 16788.495, + "args": { + "External id": 4721093,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358841089.254, "dur": 29.242, + "args": { + "External id": 4721094,"Sequence number": 47018783, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6749 + } + }, + { + "ph": "s", "id": 209, "pid": 1336753, "tid": 1336753, "ts": 1712358841089.254, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358841105.568, "dur": 7.893, + "args": { + "External id": 4721095,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358841108.420, "dur": 4.699, + "args": { + "External id": 4721096,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358841185.598, "dur": 75.409, + "args": { + "External id": 4721097,"Record function id": 0, "Ev Idx": 6752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358841262.837, "dur": 1083.677, + "args": { + "External id": 4721098,"Record function id": 0, "Ev Idx": 6753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358841303.569, "dur": 1029.087, + "args": { + "External id": 4721099,"Sequence number": 47018784, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6754 + } + }, + { + "ph": "s", "id": 208, "pid": 1336753, "tid": 1336753, "ts": 1712358841303.569, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358841371.071, "dur": 44.835, + "args": { + "External id": 4721100,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358841428.969, "dur": 99.499, + "args": { + "External id": 4721101,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358841539.695, "dur": 39.001, + "args": { + "External id": 4721102,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358841586.791, "dur": 31.509, + "args": { + "External id": 4721103,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358841644.344, "dur": 27.635, + "args": { + "External id": 4721104,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358841690.511, "dur": 14.455, + "args": { + "External id": 4721105,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358841723.607, "dur": 122.478, + "args": { + "External id": 4721106,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358841770.484, "dur": 9.882, + "args": { + "External id": 4721107,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358841774.772, "dur": 4.878, + "args": { + "External id": 4721108,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358841782.836, "dur": 5.891, + "args": { + "External id": 4721109,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358841789.842, "dur": 1.530, + "args": { + "External id": 4721110,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358841793.518, "dur": 5.665, + "args": { + "External id": 4721111,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358841856.773, "dur": 44.956, + "args": { + "External id": 4721112,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358841931.151, "dur": 31.416, + "args": { + "External id": 4721113,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358841980.339, "dur": 100.935, + "args": { + "External id": 4721114,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358842093.958, "dur": 38.360, + "args": { + "External id": 4721115,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358842158.523, "dur": 30.031, + "args": { + "External id": 4721116,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358842194.509, "dur": 34.510, + "args": { + "External id": 4721117,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358842247.802, "dur": 17.869, + "args": { + "External id": 4721118,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6773 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1712358842408.284, "dur": 73.930, + "args": { + "External id": 4721119,"Record function id": 0, "Ev Idx": 6774 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358842555.808, "dur": 46.812, + "args": { + "External id": 4721120,"Record function id": 0, "Ev Idx": 6775 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1712358842612.035, "dur": 18301.778, + "args": { + "External id": 4721121,"Record function id": 0, "Ev Idx": 6776 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1712358842620.633, "dur": 966.019, + "args": { + "External id": 4721122,"Record function id": 0, "Ev Idx": 6777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358842700.099, "dur": 7.307, + "args": { + "External id": 4721123,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358842720.482, "dur": 35.466, + "args": { + "External id": 4721124,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842725.615, "dur": 2.282, + "args": { + "External id": 4721125,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842732.216, "dur": 0.505, + "args": { + "External id": 4721126,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842733.936, "dur": 0.533, + "args": { + "External id": 4721127,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842735.706, "dur": 0.851, + "args": { + "External id": 4721128,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842739.686, "dur": 0.364, + "args": { + "External id": 4721129,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842741.173, "dur": 0.494, + "args": { + "External id": 4721130,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842742.580, "dur": 2.876, + "args": { + "External id": 4721131,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842746.561, "dur": 0.622, + "args": { + "External id": 4721132,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842748.648, "dur": 0.386, + "args": { + "External id": 4721133,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358842768.511, "dur": 37.852, + "args": { + "External id": 4721134,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358842838.728, "dur": 109.071, + "args": { + "External id": 4721135,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358842851.060, "dur": 3.724, + "args": { + "External id": 4721136,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358842859.758, "dur": 9.611, + "args": { + "External id": 4721137,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358842863.910, "dur": 5.064, + "args": { + "External id": 4721138,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842867.290, "dur": 0.576, + "args": { + "External id": 4721139,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358842875.621, "dur": 30.179, + "args": { + "External id": 4721140,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842877.285, "dur": 2.866, + "args": { + "External id": 4721141,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842881.110, "dur": 0.579, + "args": { + "External id": 4721142,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842883.029, "dur": 0.495, + "args": { + "External id": 4721143,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842887.622, "dur": 2.100, + "args": { + "External id": 4721144,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842890.733, "dur": 0.329, + "args": { + "External id": 4721145,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842892.310, "dur": 0.341, + "args": { + "External id": 4721146,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842896.382, "dur": 0.380, + "args": { + "External id": 4721147,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842897.705, "dur": 0.493, + "args": { + "External id": 4721148,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358842899.203, "dur": 2.511, + "args": { + "External id": 4721149,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358842917.191, "dur": 23.283, + "args": { + "External id": 4721150,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358843043.088, "dur": 444.003, + "args": { + "External id": 4721151,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358843092.633, "dur": 388.993, + "args": { + "External id": 4721152,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6807, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358843185.356, "dur": 290.638, + "args": { + "External id": 4721153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358843512.335, "dur": 2.269, + "args": { + "External id": 4721154,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6809, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1712358843607.393, "dur": 17088.459, + "args": { + "External id": 4721155,"Record function id": 0, "Ev Idx": 6810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843705.901, "dur": 6.685, + "args": { + "External id": 4721156,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843716.001, "dur": 1.330, + "args": { + "External id": 4721157,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843719.051, "dur": 3.469, + "args": { + "External id": 4721158,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843725.463, "dur": 0.890, + "args": { + "External id": 4721159,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843728.196, "dur": 1.048, + "args": { + "External id": 4721160,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843730.817, "dur": 0.839, + "args": { + "External id": 4721161,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843735.693, "dur": 1.100, + "args": { + "External id": 4721162,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843738.547, "dur": 2.273, + "args": { + "External id": 4721163,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843742.266, "dur": 0.966, + "args": { + "External id": 4721164,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358843744.626, "dur": 1.083, + "args": { + "External id": 4721165,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358843766.203, "dur": 16879.931, + "args": { + "External id": 4721166,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358843781.591, "dur": 16855.770, + "args": { + "External id": 4721167,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358843798.961, "dur": 14.255, + "args": { + "External id": 4721168,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358843816.212, "dur": 16782.146, + "args": { + "External id": 4721169,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358843818.517, "dur": 16778.986, + "args": { + "External id": 4721170,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358843824.518, "dur": 7.693, + "args": { + "External id": 4721171,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358843833.699, "dur": 16760.447, + "args": { + "External id": 4721172,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358860848.464, "dur": 39.045, + "args": { + "External id": 4721173,"Sequence number": 47018785, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6828 + } + }, + { + "ph": "s", "id": 207, "pid": 1336753, "tid": 1336753, "ts": 1712358860848.464, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358860872.524, "dur": 9.942, + "args": { + "External id": 4721174,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358860877.027, "dur": 5.266, + "args": { + "External id": 4721175,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358860955.730, "dur": 106.423, + "args": { + "External id": 4721176,"Record function id": 0, "Ev Idx": 6831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358861077.154, "dur": 1071.022, + "args": { + "External id": 4721177,"Record function id": 0, "Ev Idx": 6832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358861122.697, "dur": 1011.497, + "args": { + "External id": 4721178,"Sequence number": 47018786, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6833 + } + }, + { + "ph": "s", "id": 206, "pid": 1336753, "tid": 1336753, "ts": 1712358861122.697, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358861192.754, "dur": 45.096, + "args": { + "External id": 4721179,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358861252.070, "dur": 98.388, + "args": { + "External id": 4721180,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358861361.945, "dur": 38.514, + "args": { + "External id": 4721181,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358861408.621, "dur": 30.172, + "args": { + "External id": 4721182,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358861464.634, "dur": 25.869, + "args": { + "External id": 4721183,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358861508.355, "dur": 16.807, + "args": { + "External id": 4721184,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358861543.980, "dur": 129.535, + "args": { + "External id": 4721185,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358861594.267, "dur": 10.772, + "args": { + "External id": 4721186,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358861599.241, "dur": 5.044, + "args": { + "External id": 4721187,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358861607.988, "dur": 5.576, + "args": { + "External id": 4721188,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358861614.914, "dur": 1.104, + "args": { + "External id": 4721189,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358861618.213, "dur": 5.907, + "args": { + "External id": 4721190,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358861683.716, "dur": 42.780, + "args": { + "External id": 4721191,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358861755.658, "dur": 29.549, + "args": { + "External id": 4721192,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358861795.483, "dur": 39.252, + "args": { + "External id": 4721193,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358861842.856, "dur": 34.074, + "args": { + "External id": 4721194,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358861899.026, "dur": 29.956, + "args": { + "External id": 4721195,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358861934.532, "dur": 33.083, + "args": { + "External id": 4721196,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358862024.079, "dur": 23.119, + "args": { + "External id": 4721197,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6852 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1712358862213.624, "dur": 75.374, + "args": { + "External id": 4721198,"Record function id": 0, "Ev Idx": 6853 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358862364.036, "dur": 48.115, + "args": { + "External id": 4721199,"Record function id": 0, "Ev Idx": 6854 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1712358862421.968, "dur": 18862.198, + "args": { + "External id": 4721200,"Record function id": 0, "Ev Idx": 6855 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1712358862430.787, "dur": 898.954, + "args": { + "External id": 4721201,"Record function id": 0, "Ev Idx": 6856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358862509.148, "dur": 8.103, + "args": { + "External id": 4721202,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358862531.413, "dur": 39.782, + "args": { + "External id": 4721203,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862537.034, "dur": 2.376, + "args": { + "External id": 4721204,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862544.413, "dur": 0.605, + "args": { + "External id": 4721205,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862547.066, "dur": 0.596, + "args": { + "External id": 4721206,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862549.183, "dur": 0.352, + "args": { + "External id": 4721207,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862553.471, "dur": 0.309, + "args": { + "External id": 4721208,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862555.721, "dur": 0.569, + "args": { + "External id": 4721209,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862557.856, "dur": 2.757, + "args": { + "External id": 4721210,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862562.806, "dur": 0.365, + "args": { + "External id": 4721211,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862564.395, "dur": 0.504, + "args": { + "External id": 4721212,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358862585.794, "dur": 41.497, + "args": { + "External id": 4721213,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358862660.472, "dur": 116.468, + "args": { + "External id": 4721214,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358862673.310, "dur": 5.253, + "args": { + "External id": 4721215,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358862683.931, "dur": 10.252, + "args": { + "External id": 4721216,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358862687.983, "dur": 5.608, + "args": { + "External id": 4721217,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862691.780, "dur": 0.604, + "args": { + "External id": 4721218,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358862700.713, "dur": 32.024, + "args": { + "External id": 4721219,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862703.248, "dur": 0.482, + "args": { + "External id": 4721220,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862705.589, "dur": 2.634, + "args": { + "External id": 4721221,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862709.508, "dur": 0.413, + "args": { + "External id": 4721222,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862711.481, "dur": 2.014, + "args": { + "External id": 4721223,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862717.512, "dur": 0.310, + "args": { + "External id": 4721224,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862719.805, "dur": 0.543, + "args": { + "External id": 4721225,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862721.898, "dur": 0.760, + "args": { + "External id": 4721226,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862725.805, "dur": 0.625, + "args": { + "External id": 4721227,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358862727.874, "dur": 0.632, + "args": { + "External id": 4721228,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358862744.985, "dur": 24.425, + "args": { + "External id": 4721229,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358862827.156, "dur": 400.821, + "args": { + "External id": 4721230,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358862861.055, "dur": 361.470, + "args": { + "External id": 4721231,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6886, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358862870.513, "dur": 345.499, + "args": { + "External id": 4721232,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358863255.586, "dur": 2.300, + "args": { + "External id": 4721233,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6888, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1712358863350.260, "dur": 17702.615, + "args": { + "External id": 4721234,"Record function id": 0, "Ev Idx": 6889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863446.972, "dur": 6.323, + "args": { + "External id": 4721235,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863456.573, "dur": 1.422, + "args": { + "External id": 4721236,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863459.726, "dur": 2.391, + "args": { + "External id": 4721237,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863463.979, "dur": 0.917, + "args": { + "External id": 4721238,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863466.136, "dur": 0.867, + "args": { + "External id": 4721239,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863468.063, "dur": 1.001, + "args": { + "External id": 4721240,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863473.663, "dur": 1.029, + "args": { + "External id": 4721241,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863476.198, "dur": 2.074, + "args": { + "External id": 4721242,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863479.907, "dur": 0.945, + "args": { + "External id": 4721243,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358863482.853, "dur": 0.671, + "args": { + "External id": 4721244,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358863503.053, "dur": 17503.790, + "args": { + "External id": 4721245,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358863518.709, "dur": 17458.190, + "args": { + "External id": 4721246,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358863540.154, "dur": 13.646, + "args": { + "External id": 4721247,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358863556.648, "dur": 17384.434, + "args": { + "External id": 4721248,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358863559.185, "dur": 17381.139, + "args": { + "External id": 4721249,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358863565.725, "dur": 6.511, + "args": { + "External id": 4721250,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358863573.776, "dur": 17363.257, + "args": { + "External id": 4721251,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358881217.609, "dur": 39.735, + "args": { + "External id": 4721252,"Sequence number": 47018787, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6907 + } + }, + { + "ph": "s", "id": 205, "pid": 1336753, "tid": 1336753, "ts": 1712358881217.609, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358881243.133, "dur": 9.586, + "args": { + "External id": 4721253,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358881247.379, "dur": 5.009, + "args": { + "External id": 4721254,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358881326.388, "dur": 76.011, + "args": { + "External id": 4721255,"Record function id": 0, "Ev Idx": 6910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358881403.927, "dur": 1070.064, + "args": { + "External id": 4721256,"Record function id": 0, "Ev Idx": 6911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358881444.995, "dur": 1015.353, + "args": { + "External id": 4721257,"Sequence number": 47018788, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6912 + } + }, + { + "ph": "s", "id": 204, "pid": 1336753, "tid": 1336753, "ts": 1712358881444.995, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358881508.179, "dur": 44.591, + "args": { + "External id": 4721258,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358881565.555, "dur": 99.450, + "args": { + "External id": 4721259,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358881674.427, "dur": 38.636, + "args": { + "External id": 4721260,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358881720.529, "dur": 31.562, + "args": { + "External id": 4721261,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358881777.339, "dur": 27.358, + "args": { + "External id": 4721262,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358881823.370, "dur": 16.074, + "args": { + "External id": 4721263,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358881857.217, "dur": 123.115, + "args": { + "External id": 4721264,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358881904.632, "dur": 10.027, + "args": { + "External id": 4721265,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358881909.414, "dur": 4.405, + "args": { + "External id": 4721266,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358881917.437, "dur": 5.707, + "args": { + "External id": 4721267,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358881924.418, "dur": 0.865, + "args": { + "External id": 4721268,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358881927.535, "dur": 4.461, + "args": { + "External id": 4721269,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358882032.674, "dur": 66.542, + "args": { + "External id": 4721270,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358882133.542, "dur": 33.233, + "args": { + "External id": 4721271,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358882177.850, "dur": 43.663, + "args": { + "External id": 4721272,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358882229.410, "dur": 34.239, + "args": { + "External id": 4721273,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358882286.615, "dur": 27.207, + "args": { + "External id": 4721274,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358882319.256, "dur": 33.682, + "args": { + "External id": 4721275,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358882372.349, "dur": 20.522, + "args": { + "External id": 4721276,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6931 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1712358882535.828, "dur": 75.841, + "args": { + "External id": 4721277,"Record function id": 0, "Ev Idx": 6932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358882684.984, "dur": 47.463, + "args": { + "External id": 4721278,"Record function id": 0, "Ev Idx": 6933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1712358882741.967, "dur": 18639.964, + "args": { + "External id": 4721279,"Record function id": 0, "Ev Idx": 6934 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1712358882751.059, "dur": 874.125, + "args": { + "External id": 4721280,"Record function id": 0, "Ev Idx": 6935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358882830.142, "dur": 7.254, + "args": { + "External id": 4721281,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358882852.768, "dur": 40.697, + "args": { + "External id": 4721282,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358882858.938, "dur": 2.512, + "args": { + "External id": 4721283,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358882865.809, "dur": 0.455, + "args": { + "External id": 4721284,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358882868.192, "dur": 0.501, + "args": { + "External id": 4721285,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358882870.418, "dur": 2.904, + "args": { + "External id": 4721286,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358882875.004, "dur": 0.355, + "args": { + "External id": 4721287,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358882876.823, "dur": 0.322, + "args": { + "External id": 4721288,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358882881.611, "dur": 2.012, + "args": { + "External id": 4721289,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358882885.141, "dur": 0.547, + "args": { + "External id": 4721290,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358882886.991, "dur": 0.344, + "args": { + "External id": 4721291,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358882905.744, "dur": 38.048, + "args": { + "External id": 4721292,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358882974.973, "dur": 186.961, + "args": { + "External id": 4721293,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358883032.914, "dur": 6.032, + "args": { + "External id": 4721294,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358883044.637, "dur": 12.929, + "args": { + "External id": 4721295,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358883048.696, "dur": 8.409, + "args": { + "External id": 4721296,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883052.687, "dur": 2.838, + "args": { + "External id": 4721297,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358883078.871, "dur": 31.955, + "args": { + "External id": 4721298,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883081.747, "dur": 0.740, + "args": { + "External id": 4721299,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883084.374, "dur": 0.811, + "args": { + "External id": 4721300,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883086.558, "dur": 0.218, + "args": { + "External id": 4721301,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883090.350, "dur": 2.151, + "args": { + "External id": 4721302,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883093.838, "dur": 0.349, + "args": { + "External id": 4721303,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883095.562, "dur": 2.549, + "args": { + "External id": 4721304,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883099.626, "dur": 0.396, + "args": { + "External id": 4721305,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883101.664, "dur": 0.330, + "args": { + "External id": 4721306,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883105.717, "dur": 0.186, + "args": { + "External id": 4721307,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358883123.901, "dur": 29.930, + "args": { + "External id": 4721308,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358883218.424, "dur": 316.269, + "args": { + "External id": 4721309,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358883252.080, "dur": 278.272, + "args": { + "External id": 4721310,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6965, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358883261.955, "dur": 263.201, + "args": { + "External id": 4721311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358883559.174, "dur": 2.099, + "args": { + "External id": 4721312,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6967, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1712358883644.104, "dur": 17527.055, + "args": { + "External id": 4721313,"Record function id": 0, "Ev Idx": 6968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883735.723, "dur": 5.859, + "args": { + "External id": 4721314,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883744.604, "dur": 1.173, + "args": { + "External id": 4721315,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883747.387, "dur": 3.067, + "args": { + "External id": 4721316,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883752.182, "dur": 0.925, + "args": { + "External id": 4721317,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883754.898, "dur": 1.060, + "args": { + "External id": 4721318,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883757.180, "dur": 0.911, + "args": { + "External id": 4721319,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883761.750, "dur": 0.887, + "args": { + "External id": 4721320,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883764.074, "dur": 1.779, + "args": { + "External id": 4721321,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883767.504, "dur": 0.862, + "args": { + "External id": 4721322,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358883770.134, "dur": 0.632, + "args": { + "External id": 4721323,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358883790.498, "dur": 17337.511, + "args": { + "External id": 4721324,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358883805.933, "dur": 17314.813, + "args": { + "External id": 4721325,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358883828.264, "dur": 12.957, + "args": { + "External id": 4721326,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358883843.918, "dur": 17239.182, + "args": { + "External id": 4721327,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358883846.142, "dur": 17236.097, + "args": { + "External id": 4721328,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358883852.938, "dur": 6.273, + "args": { + "External id": 4721329,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358883860.991, "dur": 17217.859, + "args": { + "External id": 4721330,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358901318.337, "dur": 39.407, + "args": { + "External id": 4721331,"Sequence number": 47018789, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6986 + } + }, + { + "ph": "s", "id": 203, "pid": 1336753, "tid": 1336753, "ts": 1712358901318.337, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358901343.858, "dur": 9.290, + "args": { + "External id": 4721332,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358901348.002, "dur": 4.924, + "args": { + "External id": 4721333,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358901421.899, "dur": 75.676, + "args": { + "External id": 4721334,"Record function id": 0, "Ev Idx": 6989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358901499.172, "dur": 1087.955, + "args": { + "External id": 4721335,"Record function id": 0, "Ev Idx": 6990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358901538.764, "dur": 1036.008, + "args": { + "External id": 4721336,"Sequence number": 47018790, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6991 + } + }, + { + "ph": "s", "id": 202, "pid": 1336753, "tid": 1336753, "ts": 1712358901538.764, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358901604.399, "dur": 41.368, + "args": { + "External id": 4721337,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358901658.500, "dur": 101.364, + "args": { + "External id": 4721338,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358901769.012, "dur": 38.994, + "args": { + "External id": 4721339,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358901815.971, "dur": 31.063, + "args": { + "External id": 4721340,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358901873.137, "dur": 25.559, + "args": { + "External id": 4721341,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358901917.935, "dur": 16.645, + "args": { + "External id": 4721342,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358901951.405, "dur": 192.235, + "args": { + "External id": 4721343,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358902042.041, "dur": 11.819, + "args": { + "External id": 4721344,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358902047.274, "dur": 5.606, + "args": { + "External id": 4721345,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358902056.954, "dur": 5.341, + "args": { + "External id": 4721346,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358902077.071, "dur": 1.915, + "args": { + "External id": 4721347,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358902082.082, "dur": 5.108, + "args": { + "External id": 4721348,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358902155.558, "dur": 49.861, + "args": { + "External id": 4721349,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358902235.315, "dur": 28.270, + "args": { + "External id": 4721350,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358902273.359, "dur": 39.853, + "args": { + "External id": 4721351,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358902321.236, "dur": 33.960, + "args": { + "External id": 4721352,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358902398.664, "dur": 30.450, + "args": { + "External id": 4721353,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358902437.858, "dur": 34.895, + "args": { + "External id": 4721354,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358902490.703, "dur": 18.507, + "args": { + "External id": 4721355,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7010 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1712358902651.460, "dur": 77.357, + "args": { + "External id": 4721356,"Record function id": 0, "Ev Idx": 7011 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358902804.993, "dur": 45.946, + "args": { + "External id": 4721357,"Record function id": 0, "Ev Idx": 7012 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1712358902860.380, "dur": 18471.119, + "args": { + "External id": 4721358,"Record function id": 0, "Ev Idx": 7013 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1712358902868.944, "dur": 928.032, + "args": { + "External id": 4721359,"Record function id": 0, "Ev Idx": 7014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358902948.762, "dur": 6.674, + "args": { + "External id": 4721360,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358902969.185, "dur": 81.139, + "args": { + "External id": 4721361,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358902974.497, "dur": 2.181, + "args": { + "External id": 4721362,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903020.859, "dur": 1.041, + "args": { + "External id": 4721363,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903024.913, "dur": 0.626, + "args": { + "External id": 4721364,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903027.560, "dur": 0.564, + "args": { + "External id": 4721365,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903032.202, "dur": 0.510, + "args": { + "External id": 4721366,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903034.424, "dur": 0.259, + "args": { + "External id": 4721367,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903036.631, "dur": 2.622, + "args": { + "External id": 4721368,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903040.585, "dur": 0.644, + "args": { + "External id": 4721369,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903042.860, "dur": 0.338, + "args": { + "External id": 4721370,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358903078.687, "dur": 43.601, + "args": { + "External id": 4721371,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358903159.452, "dur": 121.857, + "args": { + "External id": 4721372,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358903173.075, "dur": 5.240, + "args": { + "External id": 4721373,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358903183.404, "dur": 10.295, + "args": { + "External id": 4721374,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358903187.542, "dur": 5.755, + "args": { + "External id": 4721375,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903191.144, "dur": 0.685, + "args": { + "External id": 4721376,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358903201.628, "dur": 33.318, + "args": { + "External id": 4721377,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903204.450, "dur": 2.811, + "args": { + "External id": 4721378,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903208.990, "dur": 0.518, + "args": { + "External id": 4721379,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903211.096, "dur": 0.460, + "args": { + "External id": 4721380,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903216.030, "dur": 1.418, + "args": { + "External id": 4721381,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903219.274, "dur": 0.297, + "args": { + "External id": 4721382,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903220.923, "dur": 0.382, + "args": { + "External id": 4721383,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903224.650, "dur": 0.156, + "args": { + "External id": 4721384,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903226.278, "dur": 0.333, + "args": { + "External id": 4721385,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358903228.453, "dur": 2.116, + "args": { + "External id": 4721386,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358903248.788, "dur": 25.132, + "args": { + "External id": 4721387,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358903335.661, "dur": 366.253, + "args": { + "External id": 4721388,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358903369.787, "dur": 327.106, + "args": { + "External id": 4721389,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7044, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358903379.895, "dur": 309.116, + "args": { + "External id": 4721390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358903728.102, "dur": 2.315, + "args": { + "External id": 4721391,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7046, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1712358903816.466, "dur": 17313.579, + "args": { + "External id": 4721392,"Record function id": 0, "Ev Idx": 7047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903912.857, "dur": 5.875, + "args": { + "External id": 4721393,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903921.970, "dur": 1.426, + "args": { + "External id": 4721394,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903925.101, "dur": 2.631, + "args": { + "External id": 4721395,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903929.233, "dur": 1.322, + "args": { + "External id": 4721396,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903931.794, "dur": 0.902, + "args": { + "External id": 4721397,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903933.910, "dur": 1.094, + "args": { + "External id": 4721398,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903938.775, "dur": 0.914, + "args": { + "External id": 4721399,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903941.246, "dur": 1.898, + "args": { + "External id": 4721400,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903944.532, "dur": 1.017, + "args": { + "External id": 4721401,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358903947.314, "dur": 0.796, + "args": { + "External id": 4721402,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358903968.247, "dur": 17120.905, + "args": { + "External id": 4721403,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358904019.486, "dur": 17062.729, + "args": { + "External id": 4721404,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358904045.047, "dur": 14.691, + "args": { + "External id": 4721405,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358904062.701, "dur": 16975.701, + "args": { + "External id": 4721406,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358904079.380, "dur": 16958.437, + "args": { + "External id": 4721407,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358904085.898, "dur": 6.165, + "args": { + "External id": 4721408,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358904093.865, "dur": 16941.312, + "args": { + "External id": 4721409,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358921271.864, "dur": 35.135, + "args": { + "External id": 4721410,"Sequence number": 47018791, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7065 + } + }, + { + "ph": "s", "id": 201, "pid": 1336753, "tid": 1336753, "ts": 1712358921271.864, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358921294.619, "dur": 7.870, + "args": { + "External id": 4721411,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358921298.058, "dur": 4.204, + "args": { + "External id": 4721412,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358921371.426, "dur": 75.233, + "args": { + "External id": 4721413,"Record function id": 0, "Ev Idx": 7068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358921448.211, "dur": 1058.255, + "args": { + "External id": 4721414,"Record function id": 0, "Ev Idx": 7069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358921488.497, "dur": 1005.002, + "args": { + "External id": 4721415,"Sequence number": 47018792, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7070 + } + }, + { + "ph": "s", "id": 200, "pid": 1336753, "tid": 1336753, "ts": 1712358921488.497, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358921553.487, "dur": 41.584, + "args": { + "External id": 4721416,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358921606.384, "dur": 98.254, + "args": { + "External id": 4721417,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358921714.805, "dur": 41.126, + "args": { + "External id": 4721418,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358921764.341, "dur": 31.353, + "args": { + "External id": 4721419,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358921820.483, "dur": 26.518, + "args": { + "External id": 4721420,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358921865.601, "dur": 15.203, + "args": { + "External id": 4721421,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358921898.183, "dur": 164.456, + "args": { + "External id": 4721422,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358921943.334, "dur": 10.259, + "args": { + "External id": 4721423,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358921948.398, "dur": 4.551, + "args": { + "External id": 4721424,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358921956.162, "dur": 5.159, + "args": { + "External id": 4721425,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358921962.626, "dur": 1.107, + "args": { + "External id": 4721426,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358921966.066, "dur": 3.595, + "args": { + "External id": 4721427,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358922088.867, "dur": 54.544, + "args": { + "External id": 4721428,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358922175.705, "dur": 29.996, + "args": { + "External id": 4721429,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358922213.962, "dur": 40.302, + "args": { + "External id": 4721430,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358922262.175, "dur": 33.709, + "args": { + "External id": 4721431,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358922319.668, "dur": 28.195, + "args": { + "External id": 4721432,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358922353.039, "dur": 33.405, + "args": { + "External id": 4721433,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358922406.122, "dur": 19.214, + "args": { + "External id": 4721434,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1712358922568.095, "dur": 72.207, + "args": { + "External id": 4721435,"Record function id": 0, "Ev Idx": 7090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358922714.482, "dur": 46.664, + "args": { + "External id": 4721436,"Record function id": 0, "Ev Idx": 7091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1712358922770.468, "dur": 18606.653, + "args": { + "External id": 4721437,"Record function id": 0, "Ev Idx": 7092 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1712358922777.709, "dur": 915.734, + "args": { + "External id": 4721438,"Record function id": 0, "Ev Idx": 7093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358922855.365, "dur": 6.904, + "args": { + "External id": 4721439,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358922876.039, "dur": 68.864, + "args": { + "External id": 4721440,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358922904.536, "dur": 2.326, + "args": { + "External id": 4721441,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358922913.038, "dur": 0.638, + "args": { + "External id": 4721442,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358922915.554, "dur": 0.586, + "args": { + "External id": 4721443,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358922917.433, "dur": 2.766, + "args": { + "External id": 4721444,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358922921.972, "dur": 0.538, + "args": { + "External id": 4721445,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358922925.985, "dur": 0.507, + "args": { + "External id": 4721446,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358922931.098, "dur": 1.502, + "args": { + "External id": 4721447,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358922934.076, "dur": 0.188, + "args": { + "External id": 4721448,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358922935.864, "dur": 2.274, + "args": { + "External id": 4721449,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358922956.641, "dur": 78.922, + "args": { + "External id": 4721450,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358923089.176, "dur": 126.227, + "args": { + "External id": 4721451,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358923103.900, "dur": 5.707, + "args": { + "External id": 4721452,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358923115.435, "dur": 11.325, + "args": { + "External id": 4721453,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358923120.052, "dur": 6.290, + "args": { + "External id": 4721454,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923124.211, "dur": 0.592, + "args": { + "External id": 4721455,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358923135.034, "dur": 30.316, + "args": { + "External id": 4721456,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923137.770, "dur": 0.541, + "args": { + "External id": 4721457,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923140.047, "dur": 0.571, + "args": { + "External id": 4721458,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923142.368, "dur": 2.293, + "args": { + "External id": 4721459,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923145.908, "dur": 1.536, + "args": { + "External id": 4721460,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923148.723, "dur": 0.532, + "args": { + "External id": 4721461,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923153.187, "dur": 0.313, + "args": { + "External id": 4721462,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923154.987, "dur": 0.322, + "args": { + "External id": 4721463,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923156.887, "dur": 0.173, + "args": { + "External id": 4721464,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923160.240, "dur": 0.554, + "args": { + "External id": 4721465,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358923178.066, "dur": 28.752, + "args": { + "External id": 4721466,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358923269.807, "dur": 337.377, + "args": { + "External id": 4721467,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358923304.683, "dur": 298.073, + "args": { + "External id": 4721468,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7123, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358923314.834, "dur": 282.220, + "args": { + "External id": 4721469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358923630.303, "dur": 2.079, + "args": { + "External id": 4721470,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7125, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1712358923714.306, "dur": 17460.560, + "args": { + "External id": 4721471,"Record function id": 0, "Ev Idx": 7126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923805.904, "dur": 5.605, + "args": { + "External id": 4721472,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923814.890, "dur": 1.281, + "args": { + "External id": 4721473,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923817.907, "dur": 2.146, + "args": { + "External id": 4721474,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923821.713, "dur": 1.050, + "args": { + "External id": 4721475,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923824.187, "dur": 0.879, + "args": { + "External id": 4721476,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923826.361, "dur": 0.975, + "args": { + "External id": 4721477,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923831.077, "dur": 1.075, + "args": { + "External id": 4721478,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923833.547, "dur": 1.919, + "args": { + "External id": 4721479,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923837.099, "dur": 0.994, + "args": { + "External id": 4721480,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358923839.970, "dur": 0.760, + "args": { + "External id": 4721481,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358923860.854, "dur": 17275.577, + "args": { + "External id": 4721482,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358923875.763, "dur": 17254.156, + "args": { + "External id": 4721483,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358923898.886, "dur": 12.903, + "args": { + "External id": 4721484,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358923914.502, "dur": 17182.285, + "args": { + "External id": 4721485,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358923917.172, "dur": 17178.917, + "args": { + "External id": 4721486,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358923923.425, "dur": 6.170, + "args": { + "External id": 4721487,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358923931.276, "dur": 17161.920, + "args": { + "External id": 4721488,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358941316.926, "dur": 35.390, + "args": { + "External id": 4721489,"Sequence number": 47018793, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7144 + } + }, + { + "ph": "s", "id": 199, "pid": 1336753, "tid": 1336753, "ts": 1712358941316.926, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358941339.885, "dur": 7.951, + "args": { + "External id": 4721490,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358941343.165, "dur": 4.451, + "args": { + "External id": 4721491,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358941416.883, "dur": 77.019, + "args": { + "External id": 4721492,"Record function id": 0, "Ev Idx": 7147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358941495.751, "dur": 1096.236, + "args": { + "External id": 4721493,"Record function id": 0, "Ev Idx": 7148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358941537.421, "dur": 1041.201, + "args": { + "External id": 4721494,"Sequence number": 47018794, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7149 + } + }, + { + "ph": "s", "id": 198, "pid": 1336753, "tid": 1336753, "ts": 1712358941537.421, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358941598.968, "dur": 38.636, + "args": { + "External id": 4721495,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358941649.977, "dur": 97.335, + "args": { + "External id": 4721496,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358941755.951, "dur": 40.151, + "args": { + "External id": 4721497,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358941804.441, "dur": 32.004, + "args": { + "External id": 4721498,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358941862.668, "dur": 27.208, + "args": { + "External id": 4721499,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358941908.086, "dur": 16.079, + "args": { + "External id": 4721500,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358941941.388, "dur": 207.257, + "args": { + "External id": 4721501,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358942042.889, "dur": 12.944, + "args": { + "External id": 4721502,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358942048.182, "dur": 6.620, + "args": { + "External id": 4721503,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358942058.763, "dur": 20.980, + "args": { + "External id": 4721504,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358942082.048, "dur": 1.854, + "args": { + "External id": 4721505,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358942086.774, "dur": 4.502, + "args": { + "External id": 4721506,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358942160.907, "dur": 54.887, + "args": { + "External id": 4721507,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358942252.693, "dur": 31.652, + "args": { + "External id": 4721508,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358942293.584, "dur": 42.018, + "args": { + "External id": 4721509,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358942344.274, "dur": 35.019, + "args": { + "External id": 4721510,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358942401.552, "dur": 28.541, + "args": { + "External id": 4721511,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358942435.724, "dur": 33.602, + "args": { + "External id": 4721512,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358942489.932, "dur": 18.435, + "args": { + "External id": 4721513,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7168 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1712358942655.645, "dur": 75.560, + "args": { + "External id": 4721514,"Record function id": 0, "Ev Idx": 7169 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358942807.299, "dur": 47.315, + "args": { + "External id": 4721515,"Record function id": 0, "Ev Idx": 7170 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1712358942864.350, "dur": 18692.050, + "args": { + "External id": 4721516,"Record function id": 0, "Ev Idx": 7171 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1712358942872.511, "dur": 921.762, + "args": { + "External id": 4721517,"Record function id": 0, "Ev Idx": 7172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358942951.026, "dur": 6.967, + "args": { + "External id": 4721518,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358942971.537, "dur": 81.937, + "args": { + "External id": 4721519,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358942976.949, "dur": 2.297, + "args": { + "External id": 4721520,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943025.732, "dur": 0.926, + "args": { + "External id": 4721521,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943029.583, "dur": 0.240, + "args": { + "External id": 4721522,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943031.525, "dur": 0.522, + "args": { + "External id": 4721523,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943035.318, "dur": 0.460, + "args": { + "External id": 4721524,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943037.421, "dur": 0.500, + "args": { + "External id": 4721525,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943039.204, "dur": 4.162, + "args": { + "External id": 4721526,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943045.225, "dur": 0.358, + "args": { + "External id": 4721527,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943047.167, "dur": 0.250, + "args": { + "External id": 4721528,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358943081.903, "dur": 42.768, + "args": { + "External id": 4721529,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358943161.923, "dur": 155.264, + "args": { + "External id": 4721530,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358943173.561, "dur": 5.009, + "args": { + "External id": 4721531,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358943183.550, "dur": 10.872, + "args": { + "External id": 4721532,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358943187.882, "dur": 6.148, + "args": { + "External id": 4721533,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943191.978, "dur": 0.701, + "args": { + "External id": 4721534,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358943202.638, "dur": 32.028, + "args": { + "External id": 4721535,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943205.139, "dur": 2.507, + "args": { + "External id": 4721536,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943209.534, "dur": 0.273, + "args": { + "External id": 4721537,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943211.292, "dur": 0.344, + "args": { + "External id": 4721538,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943214.743, "dur": 1.716, + "args": { + "External id": 4721539,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943218.096, "dur": 0.364, + "args": { + "External id": 4721540,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943219.796, "dur": 0.557, + "args": { + "External id": 4721541,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943223.763, "dur": 0.437, + "args": { + "External id": 4721542,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943225.988, "dur": 0.157, + "args": { + "External id": 4721543,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358943227.747, "dur": 2.468, + "args": { + "External id": 4721544,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358943281.375, "dur": 27.125, + "args": { + "External id": 4721545,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358943373.411, "dur": 336.703, + "args": { + "External id": 4721546,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358943408.657, "dur": 296.938, + "args": { + "External id": 4721547,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7202, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358943420.806, "dur": 279.048, + "args": { + "External id": 4721548,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358943733.310, "dur": 2.210, + "args": { + "External id": 4721549,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7204, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1712358943814.405, "dur": 17542.827, + "args": { + "External id": 4721550,"Record function id": 0, "Ev Idx": 7205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943905.728, "dur": 5.615, + "args": { + "External id": 4721551,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943914.257, "dur": 1.393, + "args": { + "External id": 4721552,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943917.169, "dur": 2.351, + "args": { + "External id": 4721553,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943921.068, "dur": 0.873, + "args": { + "External id": 4721554,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943923.370, "dur": 0.855, + "args": { + "External id": 4721555,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943925.564, "dur": 1.253, + "args": { + "External id": 4721556,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943930.727, "dur": 1.087, + "args": { + "External id": 4721557,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943933.376, "dur": 2.206, + "args": { + "External id": 4721558,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943937.123, "dur": 0.853, + "args": { + "External id": 4721559,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358943939.756, "dur": 0.717, + "args": { + "External id": 4721560,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358943960.716, "dur": 17357.619, + "args": { + "External id": 4721561,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358943976.767, "dur": 17334.552, + "args": { + "External id": 4721562,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358944048.997, "dur": 30.225, + "args": { + "External id": 4721563,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358944083.128, "dur": 17194.460, + "args": { + "External id": 4721564,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358944085.862, "dur": 17191.189, + "args": { + "External id": 4721565,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358944092.608, "dur": 6.287, + "args": { + "External id": 4721566,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358944100.450, "dur": 17174.038, + "args": { + "External id": 4721567,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358961494.855, "dur": 36.963, + "args": { + "External id": 4721568,"Sequence number": 47018795, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7223 + } + }, + { + "ph": "s", "id": 197, "pid": 1336753, "tid": 1336753, "ts": 1712358961494.855, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358961520.123, "dur": 7.049, + "args": { + "External id": 4721569,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358961523.144, "dur": 3.833, + "args": { + "External id": 4721570,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358961596.733, "dur": 74.207, + "args": { + "External id": 4721571,"Record function id": 0, "Ev Idx": 7226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358961672.463, "dur": 1071.891, + "args": { + "External id": 4721572,"Record function id": 0, "Ev Idx": 7227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358961715.108, "dur": 1016.886, + "args": { + "External id": 4721573,"Sequence number": 47018796, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7228 + } + }, + { + "ph": "s", "id": 196, "pid": 1336753, "tid": 1336753, "ts": 1712358961715.108, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358961777.460, "dur": 41.044, + "args": { + "External id": 4721574,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358961829.435, "dur": 100.291, + "args": { + "External id": 4721575,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358961938.770, "dur": 40.811, + "args": { + "External id": 4721576,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358962029.996, "dur": 53.108, + "args": { + "External id": 4721577,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358962113.145, "dur": 31.121, + "args": { + "External id": 4721578,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358962161.864, "dur": 15.797, + "args": { + "External id": 4721579,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358962197.106, "dur": 127.413, + "args": { + "External id": 4721580,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358962244.093, "dur": 11.884, + "args": { + "External id": 4721581,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358962249.584, "dur": 5.759, + "args": { + "External id": 4721582,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358962258.977, "dur": 5.924, + "args": { + "External id": 4721583,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358962266.246, "dur": 1.202, + "args": { + "External id": 4721584,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358962270.083, "dur": 4.303, + "args": { + "External id": 4721585,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358962334.705, "dur": 46.963, + "args": { + "External id": 4721586,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358962411.565, "dur": 29.353, + "args": { + "External id": 4721587,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358962449.667, "dur": 40.668, + "args": { + "External id": 4721588,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358962498.355, "dur": 35.261, + "args": { + "External id": 4721589,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358962557.378, "dur": 26.681, + "args": { + "External id": 4721590,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358962588.970, "dur": 34.373, + "args": { + "External id": 4721591,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358962641.451, "dur": 18.943, + "args": { + "External id": 4721592,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7247 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1712358962804.553, "dur": 72.991, + "args": { + "External id": 4721593,"Record function id": 0, "Ev Idx": 7248 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358962952.388, "dur": 91.414, + "args": { + "External id": 4721594,"Record function id": 0, "Ev Idx": 7249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1712358963056.328, "dur": 18443.437, + "args": { + "External id": 4721595,"Record function id": 0, "Ev Idx": 7250 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1712358963083.155, "dur": 831.687, + "args": { + "External id": 4721596,"Record function id": 0, "Ev Idx": 7251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358963167.990, "dur": 8.770, + "args": { + "External id": 4721597,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358963191.438, "dur": 40.847, + "args": { + "External id": 4721598,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963197.360, "dur": 1.894, + "args": { + "External id": 4721599,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963204.129, "dur": 0.239, + "args": { + "External id": 4721600,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963206.082, "dur": 0.502, + "args": { + "External id": 4721601,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963208.293, "dur": 0.666, + "args": { + "External id": 4721602,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963212.602, "dur": 0.443, + "args": { + "External id": 4721603,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963215.009, "dur": 0.371, + "args": { + "External id": 4721604,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963216.711, "dur": 4.353, + "args": { + "External id": 4721605,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963223.198, "dur": 0.615, + "args": { + "External id": 4721606,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963225.519, "dur": 0.312, + "args": { + "External id": 4721607,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358963247.775, "dur": 42.741, + "args": { + "External id": 4721608,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358963322.546, "dur": 113.607, + "args": { + "External id": 4721609,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358963333.074, "dur": 6.006, + "args": { + "External id": 4721610,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358963344.140, "dur": 9.905, + "args": { + "External id": 4721611,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358963348.449, "dur": 5.174, + "args": { + "External id": 4721612,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963352.077, "dur": 0.387, + "args": { + "External id": 4721613,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358963360.972, "dur": 31.072, + "args": { + "External id": 4721614,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963363.729, "dur": 0.361, + "args": { + "External id": 4721615,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963365.846, "dur": 2.644, + "args": { + "External id": 4721616,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963370.142, "dur": 0.517, + "args": { + "External id": 4721617,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963372.032, "dur": 2.505, + "args": { + "External id": 4721618,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963378.339, "dur": 0.268, + "args": { + "External id": 4721619,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963380.081, "dur": 0.312, + "args": { + "External id": 4721620,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963381.846, "dur": 0.444, + "args": { + "External id": 4721621,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963385.643, "dur": 0.288, + "args": { + "External id": 4721622,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358963387.100, "dur": 0.357, + "args": { + "External id": 4721623,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358963403.275, "dur": 25.249, + "args": { + "External id": 4721624,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358963486.852, "dur": 341.777, + "args": { + "External id": 4721625,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358963520.800, "dur": 303.156, + "args": { + "External id": 4721626,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7281, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358963531.184, "dur": 287.445, + "args": { + "External id": 4721627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358963852.621, "dur": 2.240, + "args": { + "External id": 4721628,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7283, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1712358963934.576, "dur": 17363.896, + "args": { + "External id": 4721629,"Record function id": 0, "Ev Idx": 7284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964087.427, "dur": 6.776, + "args": { + "External id": 4721630,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964098.048, "dur": 1.167, + "args": { + "External id": 4721631,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964101.024, "dur": 2.778, + "args": { + "External id": 4721632,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964105.705, "dur": 0.916, + "args": { + "External id": 4721633,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964107.939, "dur": 1.014, + "args": { + "External id": 4721634,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964110.449, "dur": 1.229, + "args": { + "External id": 4721635,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964115.444, "dur": 1.135, + "args": { + "External id": 4721636,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964118.128, "dur": 2.499, + "args": { + "External id": 4721637,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964122.182, "dur": 0.881, + "args": { + "External id": 4721638,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358964124.363, "dur": 0.704, + "args": { + "External id": 4721639,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358964145.712, "dur": 17112.324, + "args": { + "External id": 4721640,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358964162.562, "dur": 17088.498, + "args": { + "External id": 4721641,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358964187.402, "dur": 13.989, + "args": { + "External id": 4721642,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358964204.047, "dur": 17014.902, + "args": { + "External id": 4721643,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358964206.583, "dur": 17011.839, + "args": { + "External id": 4721644,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358964212.746, "dur": 5.687, + "args": { + "External id": 4721645,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358964219.929, "dur": 16995.816, + "args": { + "External id": 4721646,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358981441.238, "dur": 34.020, + "args": { + "External id": 4721647,"Sequence number": 47018797, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7302 + } + }, + { + "ph": "s", "id": 195, "pid": 1336753, "tid": 1336753, "ts": 1712358981441.238, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712358981463.923, "dur": 6.983, + "args": { + "External id": 4721648,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358981466.892, "dur": 3.771, + "args": { + "External id": 4721649,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712358981539.671, "dur": 75.023, + "args": { + "External id": 4721650,"Record function id": 0, "Ev Idx": 7305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712358981616.153, "dur": 1186.849, + "args": { + "External id": 4721651,"Record function id": 0, "Ev Idx": 7306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712358981658.306, "dur": 1130.516, + "args": { + "External id": 4721652,"Sequence number": 47018798, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7307 + } + }, + { + "ph": "s", "id": 194, "pid": 1336753, "tid": 1336753, "ts": 1712358981658.306, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358981722.667, "dur": 38.685, + "args": { + "External id": 4721653,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358981773.264, "dur": 104.008, + "args": { + "External id": 4721654,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358981887.313, "dur": 36.514, + "args": { + "External id": 4721655,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358981932.405, "dur": 32.140, + "args": { + "External id": 4721656,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358982035.315, "dur": 46.528, + "args": { + "External id": 4721657,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358982101.745, "dur": 17.509, + "args": { + "External id": 4721658,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712358982138.447, "dur": 131.334, + "args": { + "External id": 4721659,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712358982186.798, "dur": 12.479, + "args": { + "External id": 4721660,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358982192.155, "dur": 6.402, + "args": { + "External id": 4721661,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358982202.344, "dur": 5.981, + "args": { + "External id": 4721662,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358982209.879, "dur": 1.167, + "args": { + "External id": 4721663,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358982213.704, "dur": 6.301, + "args": { + "External id": 4721664,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358982355.553, "dur": 57.309, + "args": { + "External id": 4721665,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712358982451.407, "dur": 33.347, + "args": { + "External id": 4721666,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358982495.262, "dur": 47.945, + "args": { + "External id": 4721667,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358982552.740, "dur": 34.567, + "args": { + "External id": 4721668,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712358982609.434, "dur": 29.653, + "args": { + "External id": 4721669,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712358982644.671, "dur": 35.047, + "args": { + "External id": 4721670,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712358982701.556, "dur": 17.656, + "args": { + "External id": 4721671,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7326 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1712358982865.445, "dur": 74.446, + "args": { + "External id": 4721672,"Record function id": 0, "Ev Idx": 7327 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712358983056.076, "dur": 64.113, + "args": { + "External id": 4721673,"Record function id": 0, "Ev Idx": 7328 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1712358983131.464, "dur": 18258.412, + "args": { + "External id": 4721674,"Record function id": 0, "Ev Idx": 7329 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1712358983139.954, "dur": 899.016, + "args": { + "External id": 4721675,"Record function id": 0, "Ev Idx": 7330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358983220.203, "dur": 9.047, + "args": { + "External id": 4721676,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358983244.013, "dur": 40.742, + "args": { + "External id": 4721677,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983249.578, "dur": 2.262, + "args": { + "External id": 4721678,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983257.453, "dur": 0.574, + "args": { + "External id": 4721679,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983259.477, "dur": 0.806, + "args": { + "External id": 4721680,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983261.786, "dur": 0.417, + "args": { + "External id": 4721681,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983265.561, "dur": 0.424, + "args": { + "External id": 4721682,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983267.893, "dur": 0.519, + "args": { + "External id": 4721683,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983270.258, "dur": 3.659, + "args": { + "External id": 4721684,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983275.705, "dur": 0.412, + "args": { + "External id": 4721685,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983277.814, "dur": 0.359, + "args": { + "External id": 4721686,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358983297.030, "dur": 40.651, + "args": { + "External id": 4721687,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712358983370.207, "dur": 114.265, + "args": { + "External id": 4721688,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358983380.280, "dur": 4.080, + "args": { + "External id": 4721689,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712358983389.331, "dur": 10.641, + "args": { + "External id": 4721690,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712358983393.687, "dur": 5.866, + "args": { + "External id": 4721691,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983397.865, "dur": 0.582, + "args": { + "External id": 4721692,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712358983407.511, "dur": 32.109, + "args": { + "External id": 4721693,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983409.995, "dur": 2.683, + "args": { + "External id": 4721694,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983414.443, "dur": 0.243, + "args": { + "External id": 4721695,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983416.176, "dur": 0.568, + "args": { + "External id": 4721696,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983420.285, "dur": 1.517, + "args": { + "External id": 4721697,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983423.122, "dur": 0.147, + "args": { + "External id": 4721698,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983424.870, "dur": 0.321, + "args": { + "External id": 4721699,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983428.709, "dur": 0.339, + "args": { + "External id": 4721700,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983430.527, "dur": 0.369, + "args": { + "External id": 4721701,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358983432.280, "dur": 2.747, + "args": { + "External id": 4721702,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358983452.941, "dur": 24.259, + "args": { + "External id": 4721703,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712358983534.363, "dur": 373.357, + "args": { + "External id": 4721704,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358983568.117, "dur": 334.795, + "args": { + "External id": 4721705,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7360, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712358983577.508, "dur": 319.724, + "args": { + "External id": 4721706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712358983932.105, "dur": 2.239, + "args": { + "External id": 4721707,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7362, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1712358984061.892, "dur": 17127.334, + "args": { + "External id": 4721708,"Record function id": 0, "Ev Idx": 7363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984183.123, "dur": 6.798, + "args": { + "External id": 4721709,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984193.075, "dur": 1.259, + "args": { + "External id": 4721710,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984195.918, "dur": 2.640, + "args": { + "External id": 4721711,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984200.200, "dur": 1.029, + "args": { + "External id": 4721712,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984202.449, "dur": 0.967, + "args": { + "External id": 4721713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984204.554, "dur": 1.096, + "args": { + "External id": 4721714,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984209.773, "dur": 0.839, + "args": { + "External id": 4721715,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984212.088, "dur": 2.041, + "args": { + "External id": 4721716,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984215.793, "dur": 0.722, + "args": { + "External id": 4721717,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712358984218.225, "dur": 0.592, + "args": { + "External id": 4721718,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358984240.383, "dur": 16909.734, + "args": { + "External id": 4721719,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358984256.595, "dur": 16886.911, + "args": { + "External id": 4721720,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712358984299.780, "dur": 13.362, + "args": { + "External id": 4721721,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712358984315.879, "dur": 16793.725, + "args": { + "External id": 4721722,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712358984318.432, "dur": 16790.661, + "args": { + "External id": 4721723,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712358984325.227, "dur": 5.995, + "args": { + "External id": 4721724,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712358984332.646, "dur": 16773.824, + "args": { + "External id": 4721725,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359001328.060, "dur": 36.951, + "args": { + "External id": 4721726,"Sequence number": 47018799, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7381 + } + }, + { + "ph": "s", "id": 193, "pid": 1336753, "tid": 1336753, "ts": 1712359001328.060, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359001352.646, "dur": 7.868, + "args": { + "External id": 4721727,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359001356.089, "dur": 4.192, + "args": { + "External id": 4721728,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359001429.203, "dur": 72.302, + "args": { + "External id": 4721729,"Record function id": 0, "Ev Idx": 7384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359001503.024, "dur": 1085.036, + "args": { + "External id": 4721730,"Record function id": 0, "Ev Idx": 7385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359001541.133, "dur": 1033.736, + "args": { + "External id": 4721731,"Sequence number": 47018800, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7386 + } + }, + { + "ph": "s", "id": 192, "pid": 1336753, "tid": 1336753, "ts": 1712359001541.133, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359001609.807, "dur": 41.384, + "args": { + "External id": 4721732,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359001662.844, "dur": 98.738, + "args": { + "External id": 4721733,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359001771.893, "dur": 39.343, + "args": { + "External id": 4721734,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359001820.216, "dur": 31.776, + "args": { + "External id": 4721735,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359001878.588, "dur": 27.955, + "args": { + "External id": 4721736,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359001927.568, "dur": 16.229, + "args": { + "External id": 4721737,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359001961.491, "dur": 192.517, + "args": { + "External id": 4721738,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359002053.016, "dur": 27.723, + "args": { + "External id": 4721739,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359002058.466, "dur": 21.225, + "args": { + "External id": 4721740,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359002084.426, "dur": 6.356, + "args": { + "External id": 4721741,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359002092.101, "dur": 1.244, + "args": { + "External id": 4721742,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359002095.698, "dur": 4.470, + "args": { + "External id": 4721743,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359002165.821, "dur": 51.279, + "args": { + "External id": 4721744,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359002248.302, "dur": 28.836, + "args": { + "External id": 4721745,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359002286.177, "dur": 40.591, + "args": { + "External id": 4721746,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359002335.697, "dur": 35.280, + "args": { + "External id": 4721747,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359002394.269, "dur": 29.692, + "args": { + "External id": 4721748,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359002429.294, "dur": 34.583, + "args": { + "External id": 4721749,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359002483.901, "dur": 19.334, + "args": { + "External id": 4721750,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7405 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1712359002649.984, "dur": 76.649, + "args": { + "External id": 4721751,"Record function id": 0, "Ev Idx": 7406 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359002801.216, "dur": 46.991, + "args": { + "External id": 4721752,"Record function id": 0, "Ev Idx": 7407 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1712359002858.153, "dur": 18449.049, + "args": { + "External id": 4721753,"Record function id": 0, "Ev Idx": 7408 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1712359002868.810, "dur": 888.356, + "args": { + "External id": 4721754,"Record function id": 0, "Ev Idx": 7409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359002948.254, "dur": 7.100, + "args": { + "External id": 4721755,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359002968.263, "dur": 81.045, + "args": { + "External id": 4721756,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359002974.023, "dur": 2.304, + "args": { + "External id": 4721757,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003020.864, "dur": 0.988, + "args": { + "External id": 4721758,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003024.860, "dur": 0.357, + "args": { + "External id": 4721759,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003026.698, "dur": 0.223, + "args": { + "External id": 4721760,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003030.316, "dur": 0.345, + "args": { + "External id": 4721761,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003032.457, "dur": 0.500, + "args": { + "External id": 4721762,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003034.675, "dur": 4.348, + "args": { + "External id": 4721763,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003040.806, "dur": 0.352, + "args": { + "External id": 4721764,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003042.626, "dur": 0.344, + "args": { + "External id": 4721765,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359003062.723, "dur": 56.884, + "args": { + "External id": 4721766,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359003155.470, "dur": 123.507, + "args": { + "External id": 4721767,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359003171.721, "dur": 7.380, + "args": { + "External id": 4721768,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359003184.501, "dur": 10.533, + "args": { + "External id": 4721769,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359003188.628, "dur": 5.985, + "args": { + "External id": 4721770,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003192.619, "dur": 0.544, + "args": { + "External id": 4721771,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359003202.564, "dur": 31.666, + "args": { + "External id": 4721772,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003205.269, "dur": 0.343, + "args": { + "External id": 4721773,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003207.684, "dur": 2.280, + "args": { + "External id": 4721774,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003211.336, "dur": 0.400, + "args": { + "External id": 4721775,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003213.329, "dur": 2.344, + "args": { + "External id": 4721776,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003219.249, "dur": 0.370, + "args": { + "External id": 4721777,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003221.209, "dur": 0.345, + "args": { + "External id": 4721778,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003223.024, "dur": 0.496, + "args": { + "External id": 4721779,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003227.262, "dur": 0.326, + "args": { + "External id": 4721780,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359003228.781, "dur": 0.519, + "args": { + "External id": 4721781,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359003246.776, "dur": 24.777, + "args": { + "External id": 4721782,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359003331.162, "dur": 338.948, + "args": { + "External id": 4721783,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359003365.141, "dur": 300.105, + "args": { + "External id": 4721784,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7439, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359003374.598, "dur": 285.277, + "args": { + "External id": 4721785,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359003694.500, "dur": 2.120, + "args": { + "External id": 4721786,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7441, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1712359003777.410, "dur": 17332.783, + "args": { + "External id": 4721787,"Record function id": 0, "Ev Idx": 7442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003873.136, "dur": 5.749, + "args": { + "External id": 4721788,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003881.972, "dur": 1.462, + "args": { + "External id": 4721789,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003885.004, "dur": 2.695, + "args": { + "External id": 4721790,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003889.252, "dur": 1.066, + "args": { + "External id": 4721791,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003891.500, "dur": 1.008, + "args": { + "External id": 4721792,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003893.602, "dur": 0.883, + "args": { + "External id": 4721793,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003898.112, "dur": 0.643, + "args": { + "External id": 4721794,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003900.305, "dur": 2.093, + "args": { + "External id": 4721795,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003903.943, "dur": 0.735, + "args": { + "External id": 4721796,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359003906.397, "dur": 0.855, + "args": { + "External id": 4721797,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359003926.911, "dur": 17133.559, + "args": { + "External id": 4721798,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359003941.848, "dur": 17112.080, + "args": { + "External id": 4721799,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359003965.620, "dur": 13.530, + "args": { + "External id": 4721800,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359004019.856, "dur": 17000.466, + "args": { + "External id": 4721801,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359004022.366, "dur": 16997.368, + "args": { + "External id": 4721802,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359004028.816, "dur": 6.886, + "args": { + "External id": 4721803,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359004037.436, "dur": 16979.647, + "args": { + "External id": 4721804,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359021248.846, "dur": 34.416, + "args": { + "External id": 4721805,"Sequence number": 47018801, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7460 + } + }, + { + "ph": "s", "id": 191, "pid": 1336753, "tid": 1336753, "ts": 1712359021248.846, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359021270.680, "dur": 7.765, + "args": { + "External id": 4721806,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359021273.966, "dur": 4.228, + "args": { + "External id": 4721807,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359021348.039, "dur": 75.560, + "args": { + "External id": 4721808,"Record function id": 0, "Ev Idx": 7463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359021425.471, "dur": 1057.723, + "args": { + "External id": 4721809,"Record function id": 0, "Ev Idx": 7464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359021466.950, "dur": 1002.857, + "args": { + "External id": 4721810,"Sequence number": 47018802, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7465 + } + }, + { + "ph": "s", "id": 190, "pid": 1336753, "tid": 1336753, "ts": 1712359021466.950, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359021533.815, "dur": 40.910, + "args": { + "External id": 4721811,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359021587.736, "dur": 97.264, + "args": { + "External id": 4721812,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359021694.392, "dur": 35.618, + "args": { + "External id": 4721813,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359021735.794, "dur": 31.257, + "args": { + "External id": 4721814,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359021793.727, "dur": 25.226, + "args": { + "External id": 4721815,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359021834.905, "dur": 18.938, + "args": { + "External id": 4721816,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359021868.471, "dur": 170.791, + "args": { + "External id": 4721817,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359021917.013, "dur": 10.489, + "args": { + "External id": 4721818,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359021921.658, "dur": 5.154, + "args": { + "External id": 4721819,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359021930.187, "dur": 5.654, + "args": { + "External id": 4721820,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359021937.249, "dur": 3.341, + "args": { + "External id": 4721821,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359021942.907, "dur": 4.592, + "args": { + "External id": 4721822,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359022051.923, "dur": 66.815, + "args": { + "External id": 4721823,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359022155.111, "dur": 29.350, + "args": { + "External id": 4721824,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359022194.062, "dur": 42.120, + "args": { + "External id": 4721825,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359022242.909, "dur": 34.661, + "args": { + "External id": 4721826,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359022303.397, "dur": 26.411, + "args": { + "External id": 4721827,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359022334.756, "dur": 31.675, + "args": { + "External id": 4721828,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359022383.684, "dur": 20.254, + "args": { + "External id": 4721829,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7484 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1712359022544.324, "dur": 75.491, + "args": { + "External id": 4721830,"Record function id": 0, "Ev Idx": 7485 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359022694.106, "dur": 47.401, + "args": { + "External id": 4721831,"Record function id": 0, "Ev Idx": 7486 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1712359022751.309, "dur": 18426.610, + "args": { + "External id": 4721832,"Record function id": 0, "Ev Idx": 7487 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1712359022761.290, "dur": 914.737, + "args": { + "External id": 4721833,"Record function id": 0, "Ev Idx": 7488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359022842.333, "dur": 7.559, + "args": { + "External id": 4721834,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359022863.234, "dur": 39.527, + "args": { + "External id": 4721835,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359022868.667, "dur": 1.995, + "args": { + "External id": 4721836,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359022875.577, "dur": 0.499, + "args": { + "External id": 4721837,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359022877.950, "dur": 0.360, + "args": { + "External id": 4721838,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359022879.892, "dur": 0.421, + "args": { + "External id": 4721839,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359022883.940, "dur": 0.562, + "args": { + "External id": 4721840,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359022886.046, "dur": 0.248, + "args": { + "External id": 4721841,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359022887.663, "dur": 4.210, + "args": { + "External id": 4721842,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359022893.758, "dur": 0.324, + "args": { + "External id": 4721843,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359022895.940, "dur": 0.233, + "args": { + "External id": 4721844,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359022915.784, "dur": 38.745, + "args": { + "External id": 4721845,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359023025.810, "dur": 143.216, + "args": { + "External id": 4721846,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359023038.381, "dur": 5.378, + "args": { + "External id": 4721847,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359023049.098, "dur": 10.985, + "args": { + "External id": 4721848,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359023053.677, "dur": 6.003, + "args": { + "External id": 4721849,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023057.627, "dur": 0.603, + "args": { + "External id": 4721850,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359023083.808, "dur": 33.148, + "args": { + "External id": 4721851,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023086.852, "dur": 2.862, + "args": { + "External id": 4721852,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023091.712, "dur": 0.403, + "args": { + "External id": 4721853,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023093.639, "dur": 0.531, + "args": { + "External id": 4721854,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023098.104, "dur": 1.697, + "args": { + "External id": 4721855,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023101.149, "dur": 0.319, + "args": { + "External id": 4721856,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023102.997, "dur": 0.264, + "args": { + "External id": 4721857,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023107.154, "dur": 0.179, + "args": { + "External id": 4721858,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023108.662, "dur": 0.184, + "args": { + "External id": 4721859,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023110.416, "dur": 2.392, + "args": { + "External id": 4721860,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359023132.448, "dur": 28.659, + "args": { + "External id": 4721861,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359023223.574, "dur": 358.160, + "args": { + "External id": 4721862,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359023258.469, "dur": 317.869, + "args": { + "External id": 4721863,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7518, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359023268.616, "dur": 301.894, + "args": { + "External id": 4721864,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359023608.287, "dur": 2.205, + "args": { + "External id": 4721865,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7520, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1712359023696.672, "dur": 17233.938, + "args": { + "External id": 4721866,"Record function id": 0, "Ev Idx": 7521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023797.882, "dur": 6.007, + "args": { + "External id": 4721867,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023820.832, "dur": 1.188, + "args": { + "External id": 4721868,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023823.846, "dur": 2.598, + "args": { + "External id": 4721869,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023830.191, "dur": 1.028, + "args": { + "External id": 4721870,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023832.600, "dur": 0.960, + "args": { + "External id": 4721871,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023834.702, "dur": 0.937, + "args": { + "External id": 4721872,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023837.371, "dur": 0.783, + "args": { + "External id": 4721873,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023842.166, "dur": 1.864, + "args": { + "External id": 4721874,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023845.390, "dur": 0.631, + "args": { + "External id": 4721875,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359023847.537, "dur": 0.516, + "args": { + "External id": 4721876,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359023867.638, "dur": 17022.958, + "args": { + "External id": 4721877,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359023883.854, "dur": 17000.479, + "args": { + "External id": 4721878,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359023902.763, "dur": 12.800, + "args": { + "External id": 4721879,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359023920.446, "dur": 16931.196, + "args": { + "External id": 4721880,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359023923.173, "dur": 16927.988, + "args": { + "External id": 4721881,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359023929.627, "dur": 5.538, + "args": { + "External id": 4721882,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359023936.560, "dur": 16911.744, + "args": { + "External id": 4721883,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359041113.350, "dur": 38.384, + "args": { + "External id": 4721884,"Sequence number": 47018803, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7539 + } + }, + { + "ph": "s", "id": 189, "pid": 1336753, "tid": 1336753, "ts": 1712359041113.350, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359041139.020, "dur": 7.671, + "args": { + "External id": 4721885,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359041142.277, "dur": 4.024, + "args": { + "External id": 4721886,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359041218.757, "dur": 72.956, + "args": { + "External id": 4721887,"Record function id": 0, "Ev Idx": 7542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359041293.326, "dur": 1075.481, + "args": { + "External id": 4721888,"Record function id": 0, "Ev Idx": 7543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359041331.787, "dur": 1022.539, + "args": { + "External id": 4721889,"Sequence number": 47018804, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7544 + } + }, + { + "ph": "s", "id": 188, "pid": 1336753, "tid": 1336753, "ts": 1712359041331.787, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359041399.949, "dur": 42.801, + "args": { + "External id": 4721890,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359041455.461, "dur": 103.663, + "args": { + "External id": 4721891,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359041568.915, "dur": 39.016, + "args": { + "External id": 4721892,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359041615.642, "dur": 31.139, + "args": { + "External id": 4721893,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359041670.041, "dur": 26.915, + "args": { + "External id": 4721894,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359041717.433, "dur": 14.665, + "args": { + "External id": 4721895,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359041749.228, "dur": 124.014, + "args": { + "External id": 4721896,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359041795.677, "dur": 11.446, + "args": { + "External id": 4721897,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359041800.778, "dur": 5.448, + "args": { + "External id": 4721898,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359041809.994, "dur": 5.773, + "args": { + "External id": 4721899,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359041817.412, "dur": 1.543, + "args": { + "External id": 4721900,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359041821.558, "dur": 4.580, + "args": { + "External id": 4721901,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359041883.738, "dur": 45.025, + "args": { + "External id": 4721902,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359041958.865, "dur": 69.471, + "args": { + "External id": 4721903,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359042040.941, "dur": 60.068, + "args": { + "External id": 4721904,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359042113.234, "dur": 36.751, + "args": { + "External id": 4721905,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359042172.696, "dur": 28.519, + "args": { + "External id": 4721906,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359042206.971, "dur": 33.764, + "args": { + "External id": 4721907,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359042262.528, "dur": 18.981, + "args": { + "External id": 4721908,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7563 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1712359042430.551, "dur": 70.756, + "args": { + "External id": 4721909,"Record function id": 0, "Ev Idx": 7564 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359042573.524, "dur": 44.484, + "args": { + "External id": 4721910,"Record function id": 0, "Ev Idx": 7565 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1712359042628.538, "dur": 18333.335, + "args": { + "External id": 4721911,"Record function id": 0, "Ev Idx": 7566 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1712359042636.716, "dur": 877.998, + "args": { + "External id": 4721912,"Record function id": 0, "Ev Idx": 7567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359042716.011, "dur": 7.599, + "args": { + "External id": 4721913,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359042736.728, "dur": 38.152, + "args": { + "External id": 4721914,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042741.969, "dur": 2.050, + "args": { + "External id": 4721915,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042748.880, "dur": 0.424, + "args": { + "External id": 4721916,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042750.996, "dur": 0.325, + "args": { + "External id": 4721917,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042753.087, "dur": 0.431, + "args": { + "External id": 4721918,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042756.873, "dur": 0.503, + "args": { + "External id": 4721919,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042759.174, "dur": 0.308, + "args": { + "External id": 4721920,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042761.093, "dur": 4.173, + "args": { + "External id": 4721921,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042766.958, "dur": 0.329, + "args": { + "External id": 4721922,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042768.951, "dur": 0.175, + "args": { + "External id": 4721923,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359042786.408, "dur": 36.460, + "args": { + "External id": 4721924,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359042854.550, "dur": 117.602, + "args": { + "External id": 4721925,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359042864.589, "dur": 4.159, + "args": { + "External id": 4721926,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359042874.088, "dur": 9.915, + "args": { + "External id": 4721927,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359042878.462, "dur": 5.120, + "args": { + "External id": 4721928,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042882.076, "dur": 0.465, + "args": { + "External id": 4721929,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359042891.047, "dur": 37.695, + "args": { + "External id": 4721930,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042893.608, "dur": 2.459, + "args": { + "External id": 4721931,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042898.052, "dur": 0.626, + "args": { + "External id": 4721932,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042903.907, "dur": 0.569, + "args": { + "External id": 4721933,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042908.135, "dur": 2.416, + "args": { + "External id": 4721934,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042911.888, "dur": 0.444, + "args": { + "External id": 4721935,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042914.333, "dur": 2.507, + "args": { + "External id": 4721936,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042918.401, "dur": 0.150, + "args": { + "External id": 4721937,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042920.448, "dur": 0.151, + "args": { + "External id": 4721938,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359042924.494, "dur": 0.136, + "args": { + "External id": 4721939,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359042940.020, "dur": 24.861, + "args": { + "External id": 4721940,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359043081.587, "dur": 341.389, + "args": { + "External id": 4721941,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359043117.607, "dur": 300.429, + "args": { + "External id": 4721942,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7597, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359043128.462, "dur": 283.861, + "args": { + "External id": 4721943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359043446.768, "dur": 2.068, + "args": { + "External id": 4721944,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7599, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1712359043535.121, "dur": 17221.085, + "args": { + "External id": 4721945,"Record function id": 0, "Ev Idx": 7600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043637.670, "dur": 6.224, + "args": { + "External id": 4721946,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043646.780, "dur": 1.387, + "args": { + "External id": 4721947,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043649.662, "dur": 2.843, + "args": { + "External id": 4721948,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043654.028, "dur": 1.093, + "args": { + "External id": 4721949,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043656.657, "dur": 1.069, + "args": { + "External id": 4721950,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043658.995, "dur": 0.898, + "args": { + "External id": 4721951,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043663.786, "dur": 0.983, + "args": { + "External id": 4721952,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043666.274, "dur": 2.228, + "args": { + "External id": 4721953,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043669.934, "dur": 0.952, + "args": { + "External id": 4721954,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359043672.381, "dur": 0.888, + "args": { + "External id": 4721955,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359043694.250, "dur": 17022.367, + "args": { + "External id": 4721956,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359043709.812, "dur": 17000.283, + "args": { + "External id": 4721957,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359043733.202, "dur": 14.141, + "args": { + "External id": 4721958,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359043750.204, "dur": 16926.962, + "args": { + "External id": 4721959,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359043752.905, "dur": 16923.537, + "args": { + "External id": 4721960,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359043759.307, "dur": 5.475, + "args": { + "External id": 4721961,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359043766.729, "dur": 16906.763, + "args": { + "External id": 4721962,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359060898.312, "dur": 39.056, + "args": { + "External id": 4721963,"Sequence number": 47018805, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7618 + } + }, + { + "ph": "s", "id": 187, "pid": 1336753, "tid": 1336753, "ts": 1712359060898.312, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359060924.468, "dur": 8.061, + "args": { + "External id": 4721964,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359060927.946, "dur": 4.407, + "args": { + "External id": 4721965,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359061026.982, "dur": 85.593, + "args": { + "External id": 4721966,"Record function id": 0, "Ev Idx": 7621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359061115.223, "dur": 1071.214, + "args": { + "External id": 4721967,"Record function id": 0, "Ev Idx": 7622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359061158.175, "dur": 1014.197, + "args": { + "External id": 4721968,"Sequence number": 47018806, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7623 + } + }, + { + "ph": "s", "id": 186, "pid": 1336753, "tid": 1336753, "ts": 1712359061158.175, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359061224.777, "dur": 43.011, + "args": { + "External id": 4721969,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359061279.945, "dur": 103.086, + "args": { + "External id": 4721970,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359061394.513, "dur": 36.863, + "args": { + "External id": 4721971,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359061437.897, "dur": 31.891, + "args": { + "External id": 4721972,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359061498.059, "dur": 26.486, + "args": { + "External id": 4721973,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359061540.377, "dur": 16.610, + "args": { + "External id": 4721974,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359061575.496, "dur": 129.198, + "args": { + "External id": 4721975,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359061622.973, "dur": 11.179, + "args": { + "External id": 4721976,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359061627.905, "dur": 5.243, + "args": { + "External id": 4721977,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359061637.470, "dur": 6.387, + "args": { + "External id": 4721978,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359061645.174, "dur": 1.300, + "args": { + "External id": 4721979,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359061651.066, "dur": 4.347, + "args": { + "External id": 4721980,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359061715.139, "dur": 44.190, + "args": { + "External id": 4721981,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359061790.433, "dur": 29.323, + "args": { + "External id": 4721982,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359061829.403, "dur": 41.810, + "args": { + "External id": 4721983,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359061878.374, "dur": 33.582, + "args": { + "External id": 4721984,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359061934.968, "dur": 28.469, + "args": { + "External id": 4721985,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359061969.429, "dur": 72.490, + "args": { + "External id": 4721986,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359062077.441, "dur": 22.103, + "args": { + "External id": 4721987,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1712359062250.047, "dur": 74.815, + "args": { + "External id": 4721988,"Record function id": 0, "Ev Idx": 7643 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359062398.316, "dur": 47.307, + "args": { + "External id": 4721989,"Record function id": 0, "Ev Idx": 7644 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1712359062455.504, "dur": 18405.607, + "args": { + "External id": 4721990,"Record function id": 0, "Ev Idx": 7645 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1712359062464.316, "dur": 946.491, + "args": { + "External id": 4721991,"Record function id": 0, "Ev Idx": 7646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359062545.081, "dur": 8.718, + "args": { + "External id": 4721992,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359062566.829, "dur": 41.005, + "args": { + "External id": 4721993,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062572.349, "dur": 2.373, + "args": { + "External id": 4721994,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062579.650, "dur": 0.377, + "args": { + "External id": 4721995,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062582.147, "dur": 0.410, + "args": { + "External id": 4721996,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062584.121, "dur": 0.307, + "args": { + "External id": 4721997,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062588.166, "dur": 0.344, + "args": { + "External id": 4721998,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062589.790, "dur": 0.307, + "args": { + "External id": 4721999,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062591.732, "dur": 4.445, + "args": { + "External id": 4722000,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062597.845, "dur": 0.198, + "args": { + "External id": 4722001,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062599.816, "dur": 0.484, + "args": { + "External id": 4722002,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359062619.605, "dur": 38.568, + "args": { + "External id": 4722003,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359062690.255, "dur": 116.346, + "args": { + "External id": 4722004,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359062700.615, "dur": 3.881, + "args": { + "External id": 4722005,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359062709.161, "dur": 10.268, + "args": { + "External id": 4722006,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359062713.558, "dur": 5.484, + "args": { + "External id": 4722007,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062717.451, "dur": 0.419, + "args": { + "External id": 4722008,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359062725.991, "dur": 35.158, + "args": { + "External id": 4722009,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062728.438, "dur": 2.946, + "args": { + "External id": 4722010,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062733.163, "dur": 0.333, + "args": { + "External id": 4722011,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062735.314, "dur": 0.441, + "args": { + "External id": 4722012,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062739.895, "dur": 1.487, + "args": { + "External id": 4722013,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062743.359, "dur": 0.540, + "args": { + "External id": 4722014,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062745.436, "dur": 0.187, + "args": { + "External id": 4722015,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062749.167, "dur": 0.288, + "args": { + "External id": 4722016,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062751.131, "dur": 0.351, + "args": { + "External id": 4722017,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359062753.449, "dur": 2.659, + "args": { + "External id": 4722018,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359062773.691, "dur": 25.050, + "args": { + "External id": 4722019,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359062894.302, "dur": 411.226, + "args": { + "External id": 4722020,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359062930.261, "dur": 370.020, + "args": { + "External id": 4722021,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7676, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359062940.990, "dur": 350.987, + "args": { + "External id": 4722022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359063333.246, "dur": 2.550, + "args": { + "External id": 4722023,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7678, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1712359063431.292, "dur": 17232.122, + "args": { + "External id": 4722024,"Record function id": 0, "Ev Idx": 7679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063536.119, "dur": 6.719, + "args": { + "External id": 4722025,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063546.132, "dur": 1.421, + "args": { + "External id": 4722026,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063549.252, "dur": 2.354, + "args": { + "External id": 4722027,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063553.462, "dur": 1.113, + "args": { + "External id": 4722028,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063555.857, "dur": 0.815, + "args": { + "External id": 4722029,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063557.886, "dur": 1.043, + "args": { + "External id": 4722030,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063562.849, "dur": 0.886, + "args": { + "External id": 4722031,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063565.219, "dur": 2.624, + "args": { + "External id": 4722032,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063569.448, "dur": 0.634, + "args": { + "External id": 4722033,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359063571.578, "dur": 0.829, + "args": { + "External id": 4722034,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359063592.924, "dur": 17033.172, + "args": { + "External id": 4722035,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359063609.124, "dur": 17010.228, + "args": { + "External id": 4722036,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359063631.238, "dur": 14.038, + "args": { + "External id": 4722037,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359063647.948, "dur": 16938.048, + "args": { + "External id": 4722038,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359063650.517, "dur": 16934.834, + "args": { + "External id": 4722039,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359063657.077, "dur": 4.878, + "args": { + "External id": 4722040,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359063663.675, "dur": 16918.732, + "args": { + "External id": 4722041,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359080799.186, "dur": 35.471, + "args": { + "External id": 4722042,"Sequence number": 47018807, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7697 + } + }, + { + "ph": "s", "id": 185, "pid": 1336753, "tid": 1336753, "ts": 1712359080799.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359080822.033, "dur": 7.650, + "args": { + "External id": 4722043,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359080825.253, "dur": 4.217, + "args": { + "External id": 4722044,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359080900.094, "dur": 73.744, + "args": { + "External id": 4722045,"Record function id": 0, "Ev Idx": 7700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359080975.259, "dur": 1103.410, + "args": { + "External id": 4722046,"Record function id": 0, "Ev Idx": 7701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359081047.712, "dur": 1003.761, + "args": { + "External id": 4722047,"Sequence number": 47018808, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7702 + } + }, + { + "ph": "s", "id": 184, "pid": 1336753, "tid": 1336753, "ts": 1712359081047.712, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359081131.563, "dur": 43.396, + "args": { + "External id": 4722048,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359081187.594, "dur": 98.180, + "args": { + "External id": 4722049,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359081296.172, "dur": 36.101, + "args": { + "External id": 4722050,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359081340.743, "dur": 31.889, + "args": { + "External id": 4722051,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359081399.117, "dur": 27.576, + "args": { + "External id": 4722052,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359081444.157, "dur": 14.985, + "args": { + "External id": 4722053,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359081477.032, "dur": 128.859, + "args": { + "External id": 4722054,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359081526.208, "dur": 11.149, + "args": { + "External id": 4722055,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359081531.314, "dur": 5.256, + "args": { + "External id": 4722056,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359081540.240, "dur": 8.090, + "args": { + "External id": 4722057,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359081549.617, "dur": 1.133, + "args": { + "External id": 4722058,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359081553.366, "dur": 4.286, + "args": { + "External id": 4722059,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359081616.232, "dur": 46.233, + "args": { + "External id": 4722060,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359081694.168, "dur": 31.524, + "args": { + "External id": 4722061,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359081734.911, "dur": 39.754, + "args": { + "External id": 4722062,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359081782.989, "dur": 35.094, + "args": { + "External id": 4722063,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359081841.376, "dur": 26.056, + "args": { + "External id": 4722064,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359081872.816, "dur": 33.681, + "args": { + "External id": 4722065,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359081925.666, "dur": 18.065, + "args": { + "External id": 4722066,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7721 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1712359082144.527, "dur": 77.710, + "args": { + "External id": 4722067,"Record function id": 0, "Ev Idx": 7722 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359082296.937, "dur": 49.064, + "args": { + "External id": 4722068,"Record function id": 0, "Ev Idx": 7723 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1712359082356.067, "dur": 18388.683, + "args": { + "External id": 4722069,"Record function id": 0, "Ev Idx": 7724 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1712359082365.623, "dur": 938.260, + "args": { + "External id": 4722070,"Record function id": 0, "Ev Idx": 7725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359082447.264, "dur": 8.209, + "args": { + "External id": 4722071,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359082469.624, "dur": 39.617, + "args": { + "External id": 4722072,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082475.251, "dur": 1.969, + "args": { + "External id": 4722073,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082481.810, "dur": 0.425, + "args": { + "External id": 4722074,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082484.173, "dur": 0.443, + "args": { + "External id": 4722075,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082486.092, "dur": 0.345, + "args": { + "External id": 4722076,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082489.920, "dur": 0.372, + "args": { + "External id": 4722077,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082491.930, "dur": 0.293, + "args": { + "External id": 4722078,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082493.515, "dur": 3.838, + "args": { + "External id": 4722079,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082499.237, "dur": 0.352, + "args": { + "External id": 4722080,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082501.463, "dur": 0.155, + "args": { + "External id": 4722081,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359082520.921, "dur": 40.051, + "args": { + "External id": 4722082,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359082592.356, "dur": 116.989, + "args": { + "External id": 4722083,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359082602.778, "dur": 4.274, + "args": { + "External id": 4722084,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359082611.970, "dur": 10.182, + "args": { + "External id": 4722085,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359082616.348, "dur": 5.400, + "args": { + "External id": 4722086,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082619.978, "dur": 0.578, + "args": { + "External id": 4722087,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359082628.751, "dur": 39.078, + "args": { + "External id": 4722088,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082631.263, "dur": 2.700, + "args": { + "External id": 4722089,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082636.236, "dur": 0.343, + "args": { + "External id": 4722090,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082638.289, "dur": 0.191, + "args": { + "External id": 4722091,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082643.260, "dur": 1.537, + "args": { + "External id": 4722092,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082646.211, "dur": 0.254, + "args": { + "External id": 4722093,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082648.818, "dur": 0.154, + "args": { + "External id": 4722094,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082652.715, "dur": 0.478, + "args": { + "External id": 4722095,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082654.862, "dur": 0.288, + "args": { + "External id": 4722096,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359082660.334, "dur": 2.511, + "args": { + "External id": 4722097,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359082679.000, "dur": 22.638, + "args": { + "External id": 4722098,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359082760.103, "dur": 436.522, + "args": { + "External id": 4722099,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359082794.329, "dur": 396.762, + "args": { + "External id": 4722100,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7755, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359082804.193, "dur": 380.069, + "args": { + "External id": 4722101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359083225.293, "dur": 2.612, + "args": { + "External id": 4722102,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7757, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1712359083324.768, "dur": 17214.653, + "args": { + "External id": 4722103,"Record function id": 0, "Ev Idx": 7758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083428.517, "dur": 6.661, + "args": { + "External id": 4722104,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083438.560, "dur": 1.207, + "args": { + "External id": 4722105,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083441.500, "dur": 2.689, + "args": { + "External id": 4722106,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083445.955, "dur": 0.871, + "args": { + "External id": 4722107,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083448.144, "dur": 0.973, + "args": { + "External id": 4722108,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083450.382, "dur": 0.889, + "args": { + "External id": 4722109,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083455.578, "dur": 0.995, + "args": { + "External id": 4722110,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083458.130, "dur": 1.988, + "args": { + "External id": 4722111,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083461.708, "dur": 0.714, + "args": { + "External id": 4722112,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359083464.044, "dur": 0.740, + "args": { + "External id": 4722113,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359083484.653, "dur": 17015.102, + "args": { + "External id": 4722114,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359083516.510, "dur": 16976.130, + "args": { + "External id": 4722115,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359083535.109, "dur": 13.810, + "args": { + "External id": 4722116,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359083551.777, "dur": 16906.975, + "args": { + "External id": 4722117,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359083554.384, "dur": 16903.759, + "args": { + "External id": 4722118,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359083560.545, "dur": 6.785, + "args": { + "External id": 4722119,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359083569.105, "dur": 16886.318, + "args": { + "External id": 4722120,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359100680.929, "dur": 37.803, + "args": { + "External id": 4722121,"Sequence number": 47018809, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7776 + } + }, + { + "ph": "s", "id": 183, "pid": 1336753, "tid": 1336753, "ts": 1712359100680.929, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359100706.840, "dur": 7.421, + "args": { + "External id": 4722122,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359100709.947, "dur": 4.106, + "args": { + "External id": 4722123,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359100783.974, "dur": 76.153, + "args": { + "External id": 4722124,"Record function id": 0, "Ev Idx": 7779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359100861.818, "dur": 1060.108, + "args": { + "External id": 4722125,"Record function id": 0, "Ev Idx": 7780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359100900.469, "dur": 1008.767, + "args": { + "External id": 4722126,"Sequence number": 47018810, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7781 + } + }, + { + "ph": "s", "id": 182, "pid": 1336753, "tid": 1336753, "ts": 1712359100900.469, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359100964.447, "dur": 75.789, + "args": { + "External id": 4722127,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359101056.302, "dur": 114.382, + "args": { + "External id": 4722128,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359101185.047, "dur": 37.463, + "args": { + "External id": 4722129,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359101231.305, "dur": 30.794, + "args": { + "External id": 4722130,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359101289.715, "dur": 28.092, + "args": { + "External id": 4722131,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359101337.731, "dur": 16.138, + "args": { + "External id": 4722132,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359101373.025, "dur": 130.512, + "args": { + "External id": 4722133,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359101423.277, "dur": 11.537, + "args": { + "External id": 4722134,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359101428.601, "dur": 5.342, + "args": { + "External id": 4722135,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359101437.835, "dur": 6.477, + "args": { + "External id": 4722136,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359101445.592, "dur": 1.455, + "args": { + "External id": 4722137,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359101449.646, "dur": 4.135, + "args": { + "External id": 4722138,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359101514.198, "dur": 42.607, + "args": { + "External id": 4722139,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359101585.532, "dur": 29.899, + "args": { + "External id": 4722140,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359101624.811, "dur": 40.511, + "args": { + "External id": 4722141,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359101673.806, "dur": 34.282, + "args": { + "External id": 4722142,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359101732.679, "dur": 28.090, + "args": { + "External id": 4722143,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359101766.473, "dur": 32.831, + "args": { + "External id": 4722144,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359101818.998, "dur": 17.932, + "args": { + "External id": 4722145,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7800 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1712359102019.126, "dur": 97.278, + "args": { + "External id": 4722146,"Record function id": 0, "Ev Idx": 7801 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359102196.666, "dur": 47.380, + "args": { + "External id": 4722147,"Record function id": 0, "Ev Idx": 7802 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1712359102253.624, "dur": 18385.575, + "args": { + "External id": 4722148,"Record function id": 0, "Ev Idx": 7803 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1712359102262.040, "dur": 960.683, + "args": { + "External id": 4722149,"Record function id": 0, "Ev Idx": 7804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359102343.119, "dur": 9.306, + "args": { + "External id": 4722150,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359102366.094, "dur": 40.692, + "args": { + "External id": 4722151,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102371.509, "dur": 2.100, + "args": { + "External id": 4722152,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102379.623, "dur": 0.479, + "args": { + "External id": 4722153,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102381.610, "dur": 0.532, + "args": { + "External id": 4722154,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102383.716, "dur": 0.284, + "args": { + "External id": 4722155,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102387.498, "dur": 0.206, + "args": { + "External id": 4722156,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102389.302, "dur": 0.554, + "args": { + "External id": 4722157,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102391.607, "dur": 4.158, + "args": { + "External id": 4722158,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102397.739, "dur": 0.427, + "args": { + "External id": 4722159,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102399.716, "dur": 0.276, + "args": { + "External id": 4722160,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359102419.297, "dur": 40.546, + "args": { + "External id": 4722161,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359102492.790, "dur": 188.533, + "args": { + "External id": 4722162,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359102502.922, "dur": 4.238, + "args": { + "External id": 4722163,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359102512.069, "dur": 10.312, + "args": { + "External id": 4722164,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359102516.341, "dur": 5.609, + "args": { + "External id": 4722165,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102520.165, "dur": 0.542, + "args": { + "External id": 4722166,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359102529.374, "dur": 35.448, + "args": { + "External id": 4722167,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102532.142, "dur": 2.499, + "args": { + "External id": 4722168,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102537.013, "dur": 0.392, + "args": { + "External id": 4722169,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102538.916, "dur": 0.471, + "args": { + "External id": 4722170,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102543.770, "dur": 1.652, + "args": { + "External id": 4722171,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102547.038, "dur": 0.300, + "args": { + "External id": 4722172,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102549.195, "dur": 0.313, + "args": { + "External id": 4722173,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102552.949, "dur": 0.471, + "args": { + "External id": 4722174,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102555.121, "dur": 0.454, + "args": { + "External id": 4722175,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359102557.285, "dur": 2.551, + "args": { + "External id": 4722176,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359102645.016, "dur": 27.390, + "args": { + "External id": 4722177,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359102733.086, "dur": 388.520, + "args": { + "External id": 4722178,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359102766.938, "dur": 349.164, + "args": { + "External id": 4722179,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7834, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359102778.743, "dur": 331.334, + "args": { + "External id": 4722180,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359103148.116, "dur": 2.907, + "args": { + "External id": 4722181,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7836, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1712359103244.072, "dur": 17194.579, + "args": { + "External id": 4722182,"Record function id": 0, "Ev Idx": 7837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103347.806, "dur": 6.345, + "args": { + "External id": 4722183,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103357.533, "dur": 1.274, + "args": { + "External id": 4722184,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103360.432, "dur": 2.921, + "args": { + "External id": 4722185,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103364.911, "dur": 0.880, + "args": { + "External id": 4722186,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103367.108, "dur": 1.498, + "args": { + "External id": 4722187,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103369.867, "dur": 0.929, + "args": { + "External id": 4722188,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103374.536, "dur": 1.080, + "args": { + "External id": 4722189,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103377.220, "dur": 1.916, + "args": { + "External id": 4722190,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103380.788, "dur": 0.978, + "args": { + "External id": 4722191,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359103383.152, "dur": 0.772, + "args": { + "External id": 4722192,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359103404.431, "dur": 16995.138, + "args": { + "External id": 4722193,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359103420.941, "dur": 16971.947, + "args": { + "External id": 4722194,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359103456.877, "dur": 13.625, + "args": { + "External id": 4722195,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359103473.458, "dur": 16885.113, + "args": { + "External id": 4722196,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359103475.716, "dur": 16882.192, + "args": { + "External id": 4722197,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359103481.763, "dur": 5.853, + "args": { + "External id": 4722198,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359103489.155, "dur": 16866.117, + "args": { + "External id": 4722199,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359120577.840, "dur": 36.586, + "args": { + "External id": 4722200,"Sequence number": 47018811, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7855 + } + }, + { + "ph": "s", "id": 181, "pid": 1336753, "tid": 1336753, "ts": 1712359120577.840, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359120602.443, "dur": 7.256, + "args": { + "External id": 4722201,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359120605.493, "dur": 3.991, + "args": { + "External id": 4722202,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359120677.221, "dur": 71.686, + "args": { + "External id": 4722203,"Record function id": 0, "Ev Idx": 7858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359120750.528, "dur": 1058.305, + "args": { + "External id": 4722204,"Record function id": 0, "Ev Idx": 7859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359120794.486, "dur": 1001.954, + "args": { + "External id": 4722205,"Sequence number": 47018812, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7860 + } + }, + { + "ph": "s", "id": 180, "pid": 1336753, "tid": 1336753, "ts": 1712359120794.486, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359120858.378, "dur": 41.957, + "args": { + "External id": 4722206,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359120912.235, "dur": 124.988, + "args": { + "External id": 4722207,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359121050.250, "dur": 56.811, + "args": { + "External id": 4722208,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359121119.376, "dur": 32.472, + "args": { + "External id": 4722209,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359121179.239, "dur": 29.263, + "args": { + "External id": 4722210,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359121225.976, "dur": 15.668, + "args": { + "External id": 4722211,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359121260.113, "dur": 124.530, + "args": { + "External id": 4722212,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359121307.907, "dur": 10.885, + "args": { + "External id": 4722213,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359121312.527, "dur": 5.564, + "args": { + "External id": 4722214,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359121321.131, "dur": 5.592, + "args": { + "External id": 4722215,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359121327.773, "dur": 1.202, + "args": { + "External id": 4722216,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359121331.148, "dur": 4.371, + "args": { + "External id": 4722217,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359121395.051, "dur": 46.516, + "args": { + "External id": 4722218,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359121471.112, "dur": 28.701, + "args": { + "External id": 4722219,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359121509.228, "dur": 39.950, + "args": { + "External id": 4722220,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359121557.892, "dur": 34.172, + "args": { + "External id": 4722221,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359121614.753, "dur": 28.482, + "args": { + "External id": 4722222,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359121648.679, "dur": 33.041, + "args": { + "External id": 4722223,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359121700.722, "dur": 19.869, + "args": { + "External id": 4722224,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7879 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1712359121868.860, "dur": 70.764, + "args": { + "External id": 4722225,"Record function id": 0, "Ev Idx": 7880 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359122056.127, "dur": 66.131, + "args": { + "External id": 4722226,"Record function id": 0, "Ev Idx": 7881 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1712359122132.684, "dur": 18286.360, + "args": { + "External id": 4722227,"Record function id": 0, "Ev Idx": 7882 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1712359122140.545, "dur": 885.042, + "args": { + "External id": 4722228,"Record function id": 0, "Ev Idx": 7883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359122223.122, "dur": 9.263, + "args": { + "External id": 4722229,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359122246.399, "dur": 33.993, + "args": { + "External id": 4722230,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122251.303, "dur": 2.028, + "args": { + "External id": 4722231,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122257.517, "dur": 0.223, + "args": { + "External id": 4722232,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122259.346, "dur": 0.463, + "args": { + "External id": 4722233,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122261.246, "dur": 0.402, + "args": { + "External id": 4722234,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122264.884, "dur": 0.402, + "args": { + "External id": 4722235,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122266.232, "dur": 0.645, + "args": { + "External id": 4722236,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122267.887, "dur": 3.638, + "args": { + "External id": 4722237,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122272.759, "dur": 0.331, + "args": { + "External id": 4722238,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122273.945, "dur": 0.330, + "args": { + "External id": 4722239,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359122292.542, "dur": 43.225, + "args": { + "External id": 4722240,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359122366.962, "dur": 107.223, + "args": { + "External id": 4722241,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359122376.920, "dur": 4.800, + "args": { + "External id": 4722242,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359122386.676, "dur": 9.861, + "args": { + "External id": 4722243,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359122390.953, "dur": 5.160, + "args": { + "External id": 4722244,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122394.246, "dur": 0.622, + "args": { + "External id": 4722245,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359122402.804, "dur": 29.262, + "args": { + "External id": 4722246,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122404.318, "dur": 2.347, + "args": { + "External id": 4722247,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122408.289, "dur": 0.707, + "args": { + "External id": 4722248,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122409.987, "dur": 0.203, + "args": { + "External id": 4722249,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122414.237, "dur": 2.030, + "args": { + "External id": 4722250,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122417.499, "dur": 0.139, + "args": { + "External id": 4722251,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122418.696, "dur": 0.322, + "args": { + "External id": 4722252,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122422.571, "dur": 0.312, + "args": { + "External id": 4722253,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122424.269, "dur": 0.150, + "args": { + "External id": 4722254,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359122425.297, "dur": 2.495, + "args": { + "External id": 4722255,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359122442.781, "dur": 23.599, + "args": { + "External id": 4722256,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359122523.405, "dur": 370.659, + "args": { + "External id": 4722257,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359122563.487, "dur": 325.354, + "args": { + "External id": 4722258,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7913, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359122572.905, "dur": 309.857, + "args": { + "External id": 4722259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359122919.342, "dur": 2.318, + "args": { + "External id": 4722260,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7915, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1712359123049.012, "dur": 17174.275, + "args": { + "External id": 4722261,"Record function id": 0, "Ev Idx": 7916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123174.770, "dur": 6.681, + "args": { + "External id": 4722262,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123191.589, "dur": 1.260, + "args": { + "External id": 4722263,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123194.682, "dur": 3.193, + "args": { + "External id": 4722264,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123201.367, "dur": 0.750, + "args": { + "External id": 4722265,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123203.697, "dur": 0.961, + "args": { + "External id": 4722266,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123206.165, "dur": 0.641, + "args": { + "External id": 4722267,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123208.559, "dur": 1.042, + "args": { + "External id": 4722268,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123213.083, "dur": 1.743, + "args": { + "External id": 4722269,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123216.231, "dur": 0.839, + "args": { + "External id": 4722270,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359123218.624, "dur": 0.770, + "args": { + "External id": 4722271,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359123239.915, "dur": 16946.480, + "args": { + "External id": 4722272,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359123255.158, "dur": 16924.195, + "args": { + "External id": 4722273,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359123273.331, "dur": 13.355, + "args": { + "External id": 4722274,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359123291.826, "dur": 16854.903, + "args": { + "External id": 4722275,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359123294.164, "dur": 16851.847, + "args": { + "External id": 4722276,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359123299.954, "dur": 6.088, + "args": { + "External id": 4722277,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359123307.522, "dur": 16835.828, + "args": { + "External id": 4722278,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359140358.676, "dur": 35.720, + "args": { + "External id": 4722279,"Sequence number": 47018813, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7934 + } + }, + { + "ph": "s", "id": 179, "pid": 1336753, "tid": 1336753, "ts": 1712359140358.676, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359140382.463, "dur": 7.042, + "args": { + "External id": 4722280,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359140385.353, "dur": 3.934, + "args": { + "External id": 4722281,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359140457.560, "dur": 74.375, + "args": { + "External id": 4722282,"Record function id": 0, "Ev Idx": 7937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359140533.381, "dur": 1090.449, + "args": { + "External id": 4722283,"Record function id": 0, "Ev Idx": 7938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359140569.558, "dur": 1040.354, + "args": { + "External id": 4722284,"Sequence number": 47018814, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7939 + } + }, + { + "ph": "s", "id": 178, "pid": 1336753, "tid": 1336753, "ts": 1712359140569.558, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359140636.823, "dur": 40.088, + "args": { + "External id": 4722285,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359140688.905, "dur": 100.019, + "args": { + "External id": 4722286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359140798.623, "dur": 37.960, + "args": { + "External id": 4722287,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359140845.008, "dur": 31.555, + "args": { + "External id": 4722288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359140900.132, "dur": 25.487, + "args": { + "External id": 4722289,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359140945.764, "dur": 17.950, + "args": { + "External id": 4722290,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359140981.096, "dur": 186.147, + "args": { + "External id": 4722291,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359141081.797, "dur": 12.294, + "args": { + "External id": 4722292,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359141086.697, "dur": 6.509, + "args": { + "External id": 4722293,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359141096.601, "dur": 5.588, + "args": { + "External id": 4722294,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359141103.580, "dur": 1.140, + "args": { + "External id": 4722295,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359141107.211, "dur": 4.095, + "args": { + "External id": 4722296,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359141178.289, "dur": 51.686, + "args": { + "External id": 4722297,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359141263.703, "dur": 32.263, + "args": { + "External id": 4722298,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359141304.859, "dur": 41.435, + "args": { + "External id": 4722299,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359141354.665, "dur": 33.503, + "args": { + "External id": 4722300,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359141433.542, "dur": 30.136, + "args": { + "External id": 4722301,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359141471.604, "dur": 34.834, + "args": { + "External id": 4722302,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359141525.854, "dur": 18.700, + "args": { + "External id": 4722303,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7958 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1712359141686.416, "dur": 74.665, + "args": { + "External id": 4722304,"Record function id": 0, "Ev Idx": 7959 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359141837.300, "dur": 49.106, + "args": { + "External id": 4722305,"Record function id": 0, "Ev Idx": 7960 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1712359141895.712, "dur": 18368.213, + "args": { + "External id": 4722306,"Record function id": 0, "Ev Idx": 7961 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1712359141906.287, "dur": 869.949, + "args": { + "External id": 4722307,"Record function id": 0, "Ev Idx": 7962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359142025.247, "dur": 9.363, + "args": { + "External id": 4722308,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359142050.349, "dur": 49.443, + "args": { + "External id": 4722309,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142056.118, "dur": 2.092, + "args": { + "External id": 4722310,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142062.928, "dur": 0.226, + "args": { + "External id": 4722311,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142078.638, "dur": 0.483, + "args": { + "External id": 4722312,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142080.859, "dur": 0.285, + "args": { + "External id": 4722313,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142084.591, "dur": 0.193, + "args": { + "External id": 4722314,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142085.720, "dur": 0.301, + "args": { + "External id": 4722315,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142086.820, "dur": 3.309, + "args": { + "External id": 4722316,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142091.473, "dur": 0.175, + "args": { + "External id": 4722317,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142093.205, "dur": 0.287, + "args": { + "External id": 4722318,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359142113.556, "dur": 41.984, + "args": { + "External id": 4722319,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359142189.955, "dur": 113.546, + "args": { + "External id": 4722320,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359142200.747, "dur": 4.936, + "args": { + "External id": 4722321,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359142210.616, "dur": 9.597, + "args": { + "External id": 4722322,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359142214.867, "dur": 4.946, + "args": { + "External id": 4722323,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142218.124, "dur": 0.425, + "args": { + "External id": 4722324,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359142226.979, "dur": 30.110, + "args": { + "External id": 4722325,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142228.981, "dur": 2.930, + "args": { + "External id": 4722326,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142232.790, "dur": 0.467, + "args": { + "External id": 4722327,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142234.621, "dur": 0.243, + "args": { + "External id": 4722328,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142238.252, "dur": 1.745, + "args": { + "External id": 4722329,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142241.749, "dur": 0.224, + "args": { + "External id": 4722330,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142243.492, "dur": 0.394, + "args": { + "External id": 4722331,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142247.677, "dur": 0.429, + "args": { + "External id": 4722332,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142249.404, "dur": 0.322, + "args": { + "External id": 4722333,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359142250.656, "dur": 2.156, + "args": { + "External id": 4722334,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359142270.685, "dur": 25.394, + "args": { + "External id": 4722335,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359142358.607, "dur": 332.676, + "args": { + "External id": 4722336,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359142390.607, "dur": 295.827, + "args": { + "External id": 4722337,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7992, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359142400.397, "dur": 280.621, + "args": { + "External id": 4722338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359142713.260, "dur": 2.061, + "args": { + "External id": 4722339,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7994, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1712359142796.181, "dur": 17256.024, + "args": { + "External id": 4722340,"Record function id": 0, "Ev Idx": 7995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142891.395, "dur": 4.909, + "args": { + "External id": 4722341,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142899.246, "dur": 1.588, + "args": { + "External id": 4722342,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142902.669, "dur": 2.183, + "args": { + "External id": 4722343,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142906.668, "dur": 0.705, + "args": { + "External id": 4722344,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142908.600, "dur": 0.990, + "args": { + "External id": 4722345,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142910.654, "dur": 0.772, + "args": { + "External id": 4722346,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142915.017, "dur": 0.801, + "args": { + "External id": 4722347,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142917.388, "dur": 2.038, + "args": { + "External id": 4722348,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142921.308, "dur": 0.842, + "args": { + "External id": 4722349,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359142923.555, "dur": 0.708, + "args": { + "External id": 4722350,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359142943.070, "dur": 17069.983, + "args": { + "External id": 4722351,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359142957.487, "dur": 17048.063, + "args": { + "External id": 4722352,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359142982.471, "dur": 49.778, + "args": { + "External id": 4722353,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359143036.582, "dur": 16913.354, + "args": { + "External id": 4722354,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 8009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359143039.337, "dur": 16910.028, + "args": { + "External id": 4722355,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 8010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359143045.463, "dur": 5.844, + "args": { + "External id": 4722356,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359143052.816, "dur": 16893.596, + "args": { + "External id": 4722357,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 8012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359160203.548, "dur": 35.897, + "args": { + "External id": 4722358,"Sequence number": 47018815, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 8013 + } + }, + { + "ph": "s", "id": 177, "pid": 1336753, "tid": 1336753, "ts": 1712359160203.548, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359160227.007, "dur": 7.706, + "args": { + "External id": 4722359,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 8014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359160230.037, "dur": 4.333, + "args": { + "External id": 4722360,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359160302.604, "dur": 72.071, + "args": { + "External id": 4722361,"Record function id": 0, "Ev Idx": 8016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359160376.173, "dur": 1083.602, + "args": { + "External id": 4722362,"Record function id": 0, "Ev Idx": 8017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359160417.075, "dur": 1029.165, + "args": { + "External id": 4722363,"Sequence number": 47018816, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 8018 + } + }, + { + "ph": "s", "id": 176, "pid": 1336753, "tid": 1336753, "ts": 1712359160417.075, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359160484.385, "dur": 45.015, + "args": { + "External id": 4722364,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359160541.570, "dur": 99.853, + "args": { + "External id": 4722365,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359160650.869, "dur": 39.186, + "args": { + "External id": 4722366,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359160698.705, "dur": 32.188, + "args": { + "External id": 4722367,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359160755.933, "dur": 27.661, + "args": { + "External id": 4722368,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359160801.733, "dur": 15.428, + "args": { + "External id": 4722369,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359160834.002, "dur": 120.490, + "args": { + "External id": 4722370,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359160880.489, "dur": 10.768, + "args": { + "External id": 4722371,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359160885.255, "dur": 5.268, + "args": { + "External id": 4722372,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359160894.022, "dur": 5.412, + "args": { + "External id": 4722373,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359160900.634, "dur": 1.545, + "args": { + "External id": 4722374,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359160904.575, "dur": 2.679, + "args": { + "External id": 4722375,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359160964.858, "dur": 85.186, + "args": { + "External id": 4722376,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359161099.745, "dur": 31.557, + "args": { + "External id": 4722377,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359161140.706, "dur": 44.359, + "args": { + "External id": 4722378,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359161194.626, "dur": 34.861, + "args": { + "External id": 4722379,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359161253.198, "dur": 43.383, + "args": { + "External id": 4722380,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 8035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359161302.414, "dur": 32.623, + "args": { + "External id": 4722381,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 8036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359161354.641, "dur": 18.029, + "args": { + "External id": 4722382,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 8037 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1712359161522.968, "dur": 78.451, + "args": { + "External id": 4722383,"Record function id": 0, "Ev Idx": 8038 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359161676.139, "dur": 47.514, + "args": { + "External id": 4722384,"Record function id": 0, "Ev Idx": 8039 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1712359161732.829, "dur": 18426.481, + "args": { + "External id": 4722385,"Record function id": 0, "Ev Idx": 8040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1712359161740.552, "dur": 908.758, + "args": { + "External id": 4722386,"Record function id": 0, "Ev Idx": 8041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359161819.753, "dur": 7.749, + "args": { + "External id": 4722387,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359161840.427, "dur": 35.885, + "args": { + "External id": 4722388,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 8043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359161846.154, "dur": 2.293, + "args": { + "External id": 4722389,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359161853.214, "dur": 0.451, + "args": { + "External id": 4722390,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359161854.488, "dur": 0.692, + "args": { + "External id": 4722391,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359161856.591, "dur": 0.609, + "args": { + "External id": 4722392,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359161860.717, "dur": 0.366, + "args": { + "External id": 4722393,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359161862.256, "dur": 0.695, + "args": { + "External id": 4722394,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359161864.305, "dur": 2.501, + "args": { + "External id": 4722395,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359161868.047, "dur": 0.616, + "args": { + "External id": 4722396,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359161869.786, "dur": 0.457, + "args": { + "External id": 4722397,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359161889.027, "dur": 37.214, + "args": { + "External id": 4722398,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 8053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359161957.793, "dur": 190.155, + "args": { + "External id": 4722399,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 8054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359161968.294, "dur": 4.625, + "args": { + "External id": 4722400,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359161978.229, "dur": 50.968, + "args": { + "External id": 4722401,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359162021.412, "dur": 7.341, + "args": { + "External id": 4722402,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 8057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162025.386, "dur": 1.609, + "args": { + "External id": 4722403,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359162037.229, "dur": 60.676, + "args": { + "External id": 4722404,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 8059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162039.665, "dur": 3.060, + "args": { + "External id": 4722405,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162043.668, "dur": 0.693, + "args": { + "External id": 4722406,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162059.592, "dur": 0.731, + "args": { + "External id": 4722407,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162077.290, "dur": 0.841, + "args": { + "External id": 4722408,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162080.138, "dur": 0.575, + "args": { + "External id": 4722409,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162081.940, "dur": 2.722, + "args": { + "External id": 4722410,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162086.282, "dur": 0.767, + "args": { + "External id": 4722411,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162088.153, "dur": 0.422, + "args": { + "External id": 4722412,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162092.068, "dur": 0.606, + "args": { + "External id": 4722413,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359162111.701, "dur": 27.786, + "args": { + "External id": 4722414,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 8069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359162202.805, "dur": 352.432, + "args": { + "External id": 4722415,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 8070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359162237.135, "dur": 312.717, + "args": { + "External id": 4722416,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8071, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359162246.830, "dur": 296.791, + "args": { + "External id": 4722417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 8072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359162580.381, "dur": 2.369, + "args": { + "External id": 4722418,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8073, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1712359162669.429, "dur": 17246.447, + "args": { + "External id": 4722419,"Record function id": 0, "Ev Idx": 8074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162769.028, "dur": 6.768, + "args": { + "External id": 4722420,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 8075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162779.194, "dur": 1.354, + "args": { + "External id": 4722421,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162788.104, "dur": 1.304, + "args": { + "External id": 4722422,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162792.904, "dur": 0.737, + "args": { + "External id": 4722423,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162795.023, "dur": 1.243, + "args": { + "External id": 4722424,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162797.693, "dur": 1.171, + "args": { + "External id": 4722425,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162800.524, "dur": 1.180, + "args": { + "External id": 4722426,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162805.473, "dur": 2.082, + "args": { + "External id": 4722427,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162808.968, "dur": 1.075, + "args": { + "External id": 4722428,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359162811.424, "dur": 0.982, + "args": { + "External id": 4722429,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359162832.080, "dur": 17044.648, + "args": { + "External id": 4722430,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359162847.844, "dur": 17022.562, + "args": { + "External id": 4722431,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359162865.404, "dur": 13.871, + "args": { + "External id": 4722432,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359162884.408, "dur": 16953.709, + "args": { + "External id": 4722433,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 8088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359162886.842, "dur": 16950.543, + "args": { + "External id": 4722434,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 8089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359162892.749, "dur": 4.990, + "args": { + "External id": 4722435,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359162899.579, "dur": 16935.202, + "args": { + "External id": 4722436,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 8091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359180096.782, "dur": 36.616, + "args": { + "External id": 4722437,"Sequence number": 47018817, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 8092 + } + }, + { + "ph": "s", "id": 175, "pid": 1336753, "tid": 1336753, "ts": 1712359180096.782, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359180119.814, "dur": 8.166, + "args": { + "External id": 4722438,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 8093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359180122.905, "dur": 4.681, + "args": { + "External id": 4722439,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359180199.693, "dur": 72.593, + "args": { + "External id": 4722440,"Record function id": 0, "Ev Idx": 8095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359180273.986, "dur": 1069.198, + "args": { + "External id": 4722441,"Record function id": 0, "Ev Idx": 8096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359180311.724, "dur": 1017.922, + "args": { + "External id": 4722442,"Sequence number": 47018818, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 8097 + } + }, + { + "ph": "s", "id": 174, "pid": 1336753, "tid": 1336753, "ts": 1712359180311.724, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359180380.232, "dur": 42.880, + "args": { + "External id": 4722443,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359180435.212, "dur": 99.708, + "args": { + "External id": 4722444,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359180543.069, "dur": 37.689, + "args": { + "External id": 4722445,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359180590.030, "dur": 32.705, + "args": { + "External id": 4722446,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359180645.344, "dur": 28.039, + "args": { + "External id": 4722447,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359180693.983, "dur": 16.745, + "args": { + "External id": 4722448,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359180726.743, "dur": 124.294, + "args": { + "External id": 4722449,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359180773.986, "dur": 10.921, + "args": { + "External id": 4722450,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359180778.616, "dur": 5.629, + "args": { + "External id": 4722451,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359180787.296, "dur": 5.882, + "args": { + "External id": 4722452,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359180794.475, "dur": 1.653, + "args": { + "External id": 4722453,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359180798.316, "dur": 3.391, + "args": { + "External id": 4722454,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359180861.815, "dur": 41.411, + "args": { + "External id": 4722455,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359180935.222, "dur": 27.868, + "args": { + "External id": 4722456,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359180971.511, "dur": 82.106, + "args": { + "External id": 4722457,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359181080.192, "dur": 40.691, + "args": { + "External id": 4722458,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359181145.097, "dur": 30.264, + "args": { + "External id": 4722459,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 8114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359181182.420, "dur": 33.620, + "args": { + "External id": 4722460,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 8115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359181237.538, "dur": 18.578, + "args": { + "External id": 4722461,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 8116 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1712359181404.443, "dur": 73.972, + "args": { + "External id": 4722462,"Record function id": 0, "Ev Idx": 8117 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1712359181552.090, "dur": 48.278, + "args": { + "External id": 4722463,"Record function id": 0, "Ev Idx": 8118 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1712359181609.505, "dur": 18526.833, + "args": { + "External id": 4722464,"Record function id": 0, "Ev Idx": 8119 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1712359181617.191, "dur": 859.625, + "args": { + "External id": 4722465,"Record function id": 0, "Ev Idx": 8120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359181694.833, "dur": 7.996, + "args": { + "External id": 4722466,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359181716.196, "dur": 34.634, + "args": { + "External id": 4722467,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 8122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181721.319, "dur": 2.021, + "args": { + "External id": 4722468,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181727.639, "dur": 0.662, + "args": { + "External id": 4722469,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181729.483, "dur": 0.587, + "args": { + "External id": 4722470,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181731.287, "dur": 0.427, + "args": { + "External id": 4722471,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181734.987, "dur": 0.600, + "args": { + "External id": 4722472,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181736.470, "dur": 0.493, + "args": { + "External id": 4722473,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181738.123, "dur": 2.544, + "args": { + "External id": 4722474,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181741.580, "dur": 0.727, + "args": { + "External id": 4722475,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181743.324, "dur": 0.909, + "args": { + "External id": 4722476,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359181763.195, "dur": 35.550, + "args": { + "External id": 4722477,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 8132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1712359181830.099, "dur": 105.373, + "args": { + "External id": 4722478,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 8133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359181839.996, "dur": 4.392, + "args": { + "External id": 4722479,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1712359181849.241, "dur": 9.333, + "args": { + "External id": 4722480,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359181853.490, "dur": 4.636, + "args": { + "External id": 4722481,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 8136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181856.460, "dur": 0.570, + "args": { + "External id": 4722482,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1712359181865.394, "dur": 28.698, + "args": { + "External id": 4722483,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 8138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181867.342, "dur": 2.612, + "args": { + "External id": 4722484,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181870.965, "dur": 0.698, + "args": { + "External id": 4722485,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181872.739, "dur": 0.826, + "args": { + "External id": 4722486,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181876.878, "dur": 0.740, + "args": { + "External id": 4722487,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181878.454, "dur": 0.406, + "args": { + "External id": 4722488,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181879.967, "dur": 1.146, + "args": { + "External id": 4722489,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181883.847, "dur": 0.673, + "args": { + "External id": 4722490,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181885.565, "dur": 0.655, + "args": { + "External id": 4722491,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359181887.274, "dur": 2.779, + "args": { + "External id": 4722492,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359181906.352, "dur": 21.114, + "args": { + "External id": 4722493,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 8148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1712359182024.916, "dur": 354.535, + "args": { + "External id": 4722494,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 8149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359182057.723, "dur": 317.524, + "args": { + "External id": 4722495,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8150, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1712359182082.850, "dur": 287.183, + "args": { + "External id": 4722496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 8151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712359182403.432, "dur": 2.009, + "args": { + "External id": 4722497,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8152, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1712359182498.154, "dur": 17390.610, + "args": { + "External id": 4722498,"Record function id": 0, "Ev Idx": 8153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182645.013, "dur": 7.111, + "args": { + "External id": 4722499,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 8154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182655.639, "dur": 1.265, + "args": { + "External id": 4722500,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182658.674, "dur": 1.400, + "args": { + "External id": 4722501,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182663.606, "dur": 0.921, + "args": { + "External id": 4722502,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182666.013, "dur": 0.943, + "args": { + "External id": 4722503,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182668.207, "dur": 1.456, + "args": { + "External id": 4722504,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182671.088, "dur": 1.065, + "args": { + "External id": 4722505,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182676.020, "dur": 2.168, + "args": { + "External id": 4722506,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182679.592, "dur": 1.232, + "args": { + "External id": 4722507,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359182682.074, "dur": 1.346, + "args": { + "External id": 4722508,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359182703.509, "dur": 17144.428, + "args": { + "External id": 4722509,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359182719.497, "dur": 17121.486, + "args": { + "External id": 4722510,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359182736.784, "dur": 12.964, + "args": { + "External id": 4722511,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359182755.363, "dur": 17050.858, + "args": { + "External id": 4722512,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 8167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359182758.263, "dur": 17047.313, + "args": { + "External id": 4722513,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 8168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359182764.190, "dur": 5.622, + "args": { + "External id": 4722514,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359182771.426, "dur": 17031.091, + "args": { + "External id": 4722515,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 8170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359200057.086, "dur": 51.734, + "args": { + "External id": 4722516,"Sequence number": 47018819, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 8171 + } + }, + { + "ph": "s", "id": 173, "pid": 1336753, "tid": 1336753, "ts": 1712359200057.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359200094.487, "dur": 9.064, + "args": { + "External id": 4722517,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 8172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359200098.156, "dur": 5.033, + "args": { + "External id": 4722518,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359200176.837, "dur": 74.771, + "args": { + "External id": 4722519,"Record function id": 0, "Ev Idx": 8174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1712359200253.151, "dur": 1087.470, + "args": { + "External id": 4722520,"Record function id": 0, "Ev Idx": 8175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359200293.514, "dur": 1034.295, + "args": { + "External id": 4722521,"Sequence number": 47018820, "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": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 8176 + } + }, + { + "ph": "s", "id": 172, "pid": 1336753, "tid": 1336753, "ts": 1712359200293.514, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359200362.254, "dur": 47.404, + "args": { + "External id": 4722522,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359200422.225, "dur": 98.010, + "args": { + "External id": 4722523,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359200528.613, "dur": 40.055, + "args": { + "External id": 4722524,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359200578.046, "dur": 31.305, + "args": { + "External id": 4722525,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359200635.796, "dur": 27.724, + "args": { + "External id": 4722526,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359200681.667, "dur": 16.250, + "args": { + "External id": 4722527,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359200714.556, "dur": 126.550, + "args": { + "External id": 4722528,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359200763.798, "dur": 12.052, + "args": { + "External id": 4722529,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359200768.954, "dur": 6.223, + "args": { + "External id": 4722530,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359200778.511, "dur": 5.614, + "args": { + "External id": 4722531,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359200785.914, "dur": 1.589, + "args": { + "External id": 4722532,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359200789.600, "dur": 3.394, + "args": { + "External id": 4722533,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359200852.237, "dur": 44.758, + "args": { + "External id": 4722534,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1712359200930.498, "dur": 29.622, + "args": { + "External id": 4722535,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359200968.554, "dur": 81.139, + "args": { + "External id": 4722536,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359201063.087, "dur": 53.905, + "args": { + "External id": 4722537,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359201144.898, "dur": 29.372, + "args": { + "External id": 4722538,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 8193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359201180.981, "dur": 35.327, + "args": { + "External id": 4722539,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 8194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1712359201236.685, "dur": 19.877, + "args": { + "External id": 4722540,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 8195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1712359201401.344, "dur": 30.916, + "args": { + "External id": 4722541,"Record function id": 0, "Ev Idx": 8196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359201577.346, "dur": 301.523, + "args": { + "External id": 4722542,"Sequence number": 47018821, "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": [[8388608, 2048, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [], [], [], [], []], "Ev Idx": 8197 + } + }, + { + "ph": "s", "id": 171, "pid": 1336753, "tid": 1336753, "ts": 1712359201577.346, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359201608.441, "dur": 7.944, + "args": { + "External id": 4722543,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359201610.895, "dur": 5.269, + "args": { + "External id": 4722544,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359201626.380, "dur": 11.234, + "args": { + "External id": 4722545,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359201629.245, "dur": 7.779, + "args": { + "External id": 4722546,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359201646.960, "dur": 5.424, + "args": { + "External id": 4722547,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359201858.480, "dur": 7.514, + "args": { + "External id": 4722548,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359201862.718, "dur": 3.036, + "args": { + "External id": 4722549,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359201909.113, "dur": 189.506, + "args": { + "External id": 4722550,"Sequence number": 47018822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359201911.505, "dur": 14.515, + "args": { + "External id": 4722551,"Sequence number": 47018822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8206 + } + }, + { + "ph": "s", "id": 170, "pid": 1336753, "tid": 1336753, "ts": 1712359201911.505, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359201917.078, "dur": 7.230, + "args": { + "External id": 4722552,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359201921.835, "dur": 2.117, + "args": { + "External id": 4722553,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359201928.299, "dur": 170.004, + "args": { + "External id": 4722554,"Sequence number": 47018823, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359201930.692, "dur": 4.072, + "args": { + "External id": 4722555,"Sequence number": 47018823, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359201931.273, "dur": 3.349, + "args": { + "External id": 4722556,"Sequence number": 47018823, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8211 + } + }, + { + "ph": "s", "id": 169, "pid": 1336753, "tid": 1336753, "ts": 1712359201931.273, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359201938.435, "dur": 148.924, + "args": { + "External id": 4722557,"Sequence number": 47018824, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8212 + } + }, + { + "ph": "s", "id": 168, "pid": 1336753, "tid": 1336753, "ts": 1712359201938.435, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202092.010, "dur": 5.084, + "args": { + "External id": 4722558,"Sequence number": 47018825, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8213 + } + }, + { + "ph": "s", "id": 167, "pid": 1336753, "tid": 1336753, "ts": 1712359202092.010, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359202111.629, "dur": 81.234, + "args": { + "External id": 4722559,"Sequence number": 47018826, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359202112.804, "dur": 10.064, + "args": { + "External id": 4722560,"Sequence number": 47018826, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8215 + } + }, + { + "ph": "s", "id": 166, "pid": 1336753, "tid": 1336753, "ts": 1712359202112.804, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359202115.102, "dur": 6.340, + "args": { + "External id": 4722561,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359202119.490, "dur": 1.659, + "args": { + "External id": 4722562,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359202123.709, "dur": 68.898, + "args": { + "External id": 4722563,"Sequence number": 47018827, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359202124.687, "dur": 6.265, + "args": { + "External id": 4722564,"Sequence number": 47018827, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202125.970, "dur": 4.846, + "args": { + "External id": 4722565,"Sequence number": 47018827, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8220 + } + }, + { + "ph": "s", "id": 165, "pid": 1336753, "tid": 1336753, "ts": 1712359202125.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359202131.769, "dur": 53.209, + "args": { + "External id": 4722566,"Sequence number": 47018828, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8221 + } + }, + { + "ph": "s", "id": 164, "pid": 1336753, "tid": 1336753, "ts": 1712359202131.769, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202186.959, "dur": 5.235, + "args": { + "External id": 4722567,"Sequence number": 47018829, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8222 + } + }, + { + "ph": "s", "id": 163, "pid": 1336753, "tid": 1336753, "ts": 1712359202186.959, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359202201.582, "dur": 66.099, + "args": { + "External id": 4722568,"Sequence number": 47018830, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359202202.092, "dur": 6.264, + "args": { + "External id": 4722569,"Sequence number": 47018830, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8224 + } + }, + { + "ph": "s", "id": 162, "pid": 1336753, "tid": 1336753, "ts": 1712359202202.092, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359202204.283, "dur": 2.959, + "args": { + "External id": 4722570,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359202205.929, "dur": 1.173, + "args": { + "External id": 4722571,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359202211.513, "dur": 55.952, + "args": { + "External id": 4722572,"Sequence number": 47018831, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359202212.546, "dur": 4.773, + "args": { + "External id": 4722573,"Sequence number": 47018831, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202213.222, "dur": 3.955, + "args": { + "External id": 4722574,"Sequence number": 47018831, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8229 + } + }, + { + "ph": "s", "id": 161, "pid": 1336753, "tid": 1336753, "ts": 1712359202213.222, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359202217.916, "dur": 41.073, + "args": { + "External id": 4722575,"Sequence number": 47018832, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8230 + } + }, + { + "ph": "s", "id": 160, "pid": 1336753, "tid": 1336753, "ts": 1712359202217.916, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202260.522, "dur": 6.559, + "args": { + "External id": 4722576,"Sequence number": 47018833, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8231 + } + }, + { + "ph": "s", "id": 159, "pid": 1336753, "tid": 1336753, "ts": 1712359202260.522, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359202291.443, "dur": 3.963, + "args": { + "External id": 4722577,"Sequence number": 47018834, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202292.487, "dur": 2.786, + "args": { + "External id": 4722578,"Sequence number": 47018834, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8233 + } + }, + { + "ph": "s", "id": 158, "pid": 1336753, "tid": 1336753, "ts": 1712359202292.487, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359202302.291, "dur": 3.669, + "args": { + "External id": 4722579,"Sequence number": 47018835, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202303.586, "dur": 2.257, + "args": { + "External id": 4722580,"Sequence number": 47018835, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8235 + } + }, + { + "ph": "s", "id": 157, "pid": 1336753, "tid": 1336753, "ts": 1712359202303.586, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359202312.985, "dur": 5.560, + "args": { + "External id": 4722581,"Sequence number": 47018836, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202314.112, "dur": 4.284, + "args": { + "External id": 4722582,"Sequence number": 47018836, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8237 + } + }, + { + "ph": "s", "id": 156, "pid": 1336753, "tid": 1336753, "ts": 1712359202314.112, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359202356.162, "dur": 186.194, + "args": { + "External id": 4722583,"Sequence number": 47018837, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8238 + } + }, + { + "ph": "s", "id": 155, "pid": 1336753, "tid": 1336753, "ts": 1712359202356.162, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359202378.541, "dur": 9.736, + "args": { + "External id": 4722584,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359202382.168, "dur": 5.622, + "args": { + "External id": 4722585,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359202555.796, "dur": 110.396, + "args": { + "External id": 4722586,"Sequence number": 47018838, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8241 + } + }, + { + "ph": "s", "id": 154, "pid": 1336753, "tid": 1336753, "ts": 1712359202555.796, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359202570.142, "dur": 7.427, + "args": { + "External id": 4722587,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359202572.827, "dur": 4.235, + "args": { + "External id": 4722588,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336753, "tid": 1336753, + "ts": 1712359202695.209, "dur": 192.192, + "args": { + "External id": 4722589,"Sequence number": 47018839, "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 8244 + } + }, + { + "ph": "s", "id": 153, "pid": 1336753, "tid": 1336753, "ts": 1712359202695.209, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359202724.999, "dur": 133.745, + "args": { + "External id": 4722590,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359202777.963, "dur": 6.811, + "args": { + "External id": 4722591,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359202779.923, "dur": 4.327, + "args": { + "External id": 4722592,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359202787.516, "dur": 4.914, + "args": { + "External id": 4722593,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359202794.095, "dur": 1.516, + "args": { + "External id": 4722594,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359202799.994, "dur": 4.177, + "args": { + "External id": 4722595,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1712359202872.242, "dur": 4.971, + "args": { + "External id": 4722596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359202893.371, "dur": 5.246, + "args": { + "External id": 4722597,"Sequence number": 47018840, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202894.811, "dur": 3.644, + "args": { + "External id": 4722598,"Sequence number": 47018840, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8253 + } + }, + { + "ph": "s", "id": 152, "pid": 1336753, "tid": 1336753, "ts": 1712359202894.811, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359202914.201, "dur": 172.653, + "args": { + "External id": 4722599,"Sequence number": 47018841, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359202918.096, "dur": 9.126, + "args": { + "External id": 4722600,"Sequence number": 47018841, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8255 + } + }, + { + "ph": "s", "id": 151, "pid": 1336753, "tid": 1336753, "ts": 1712359202918.096, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359202920.947, "dur": 5.006, + "args": { + "External id": 4722601,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359202923.596, "dur": 2.101, + "args": { + "External id": 4722602,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359202928.693, "dur": 157.895, + "args": { + "External id": 4722603,"Sequence number": 47018842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359202930.082, "dur": 9.776, + "args": { + "External id": 4722604,"Sequence number": 47018842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359202933.005, "dur": 6.694, + "args": { + "External id": 4722605,"Sequence number": 47018842, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8260 + } + }, + { + "ph": "s", "id": 150, "pid": 1336753, "tid": 1336753, "ts": 1712359202933.005, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359202940.793, "dur": 120.297, + "args": { + "External id": 4722606,"Sequence number": 47018843, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8261 + } + }, + { + "ph": "s", "id": 149, "pid": 1336753, "tid": 1336753, "ts": 1712359202940.793, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203078.811, "dur": 6.635, + "args": { + "External id": 4722607,"Sequence number": 47018844, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8262 + } + }, + { + "ph": "s", "id": 148, "pid": 1336753, "tid": 1336753, "ts": 1712359203078.811, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359203127.607, "dur": 235.310, + "args": { + "External id": 4722608,"Sequence number": 47018845, "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": [[8388608, 2048, 1], [1], [], [8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [16, 4096, 2048], [], [], [], []], "Ev Idx": 8263 + } + }, + { + "ph": "s", "id": 147, "pid": 1336753, "tid": 1336753, "ts": 1712359203127.607, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359203148.845, "dur": 3.808, + "args": { + "External id": 4722609,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203150.011, "dur": 2.449, + "args": { + "External id": 4722610,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359203158.416, "dur": 3.761, + "args": { + "External id": 4722611,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [2048, 1]], "Input Dims": [[16, 4096, 2048], [65536, 2048]], "Ev Idx": 8266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359203159.821, "dur": 2.251, + "args": { + "External id": 4722612,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203160.463, "dur": 1.501, + "args": { + "External id": 4722613,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359203170.343, "dur": 9.886, + "args": { + "External id": 4722614,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359203174.698, "dur": 5.138, + "args": { + "External id": 4722615,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359203187.060, "dur": 3.914, + "args": { + "External id": 4722616,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359203194.715, "dur": 3.356, + "args": { + "External id": 4722617,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359203336.722, "dur": 3.627, + "args": { + "External id": 4722618,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203337.655, "dur": 2.459, + "args": { + "External id": 4722619,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359203342.802, "dur": 2.392, + "args": { + "External id": 4722620,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203343.851, "dur": 1.230, + "args": { + "External id": 4722621,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359203384.885, "dur": 97.904, + "args": { + "External id": 4722622,"Sequence number": 47018846, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359203386.296, "dur": 8.362, + "args": { + "External id": 4722623,"Sequence number": 47018846, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8278 + } + }, + { + "ph": "s", "id": 146, "pid": 1336753, "tid": 1336753, "ts": 1712359203386.296, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359203388.573, "dur": 4.913, + "args": { + "External id": 4722624,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359203391.005, "dur": 2.092, + "args": { + "External id": 4722625,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359203395.443, "dur": 87.045, + "args": { + "External id": 4722626,"Sequence number": 47018847, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359203399.599, "dur": 3.375, + "args": { + "External id": 4722627,"Sequence number": 47018847, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203400.187, "dur": 2.652, + "args": { + "External id": 4722628,"Sequence number": 47018847, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8283 + } + }, + { + "ph": "s", "id": 145, "pid": 1336753, "tid": 1336753, "ts": 1712359203400.187, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359203403.959, "dur": 72.853, + "args": { + "External id": 4722629,"Sequence number": 47018848, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8284 + } + }, + { + "ph": "s", "id": 144, "pid": 1336753, "tid": 1336753, "ts": 1712359203403.959, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203478.823, "dur": 3.086, + "args": { + "External id": 4722630,"Sequence number": 47018849, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8285 + } + }, + { + "ph": "s", "id": 143, "pid": 1336753, "tid": 1336753, "ts": 1712359203478.823, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359203491.321, "dur": 73.092, + "args": { + "External id": 4722631,"Sequence number": 47018850, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359203494.192, "dur": 6.729, + "args": { + "External id": 4722632,"Sequence number": 47018850, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8287 + } + }, + { + "ph": "s", "id": 142, "pid": 1336753, "tid": 1336753, "ts": 1712359203494.192, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359203496.292, "dur": 3.553, + "args": { + "External id": 4722633,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359203498.529, "dur": 1.168, + "args": { + "External id": 4722634,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359203501.548, "dur": 62.607, + "args": { + "External id": 4722635,"Sequence number": 47018851, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359203502.563, "dur": 9.354, + "args": { + "External id": 4722636,"Sequence number": 47018851, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203505.577, "dur": 6.190, + "args": { + "External id": 4722637,"Sequence number": 47018851, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8292 + } + }, + { + "ph": "s", "id": 141, "pid": 1336753, "tid": 1336753, "ts": 1712359203505.577, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359203512.532, "dur": 44.312, + "args": { + "External id": 4722638,"Sequence number": 47018852, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8293 + } + }, + { + "ph": "s", "id": 140, "pid": 1336753, "tid": 1336753, "ts": 1712359203512.532, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203558.428, "dur": 5.370, + "args": { + "External id": 4722639,"Sequence number": 47018853, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8294 + } + }, + { + "ph": "s", "id": 139, "pid": 1336753, "tid": 1336753, "ts": 1712359203558.428, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359203586.970, "dur": 158.686, + "args": { + "External id": 4722640,"Sequence number": 47018854, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8295 + } + }, + { + "ph": "s", "id": 138, "pid": 1336753, "tid": 1336753, "ts": 1712359203586.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359203633.604, "dur": 3.512, + "args": { + "External id": 4722641,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359203672.712, "dur": 58.937, + "args": { + "External id": 4722642,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359203673.638, "dur": 5.542, + "args": { + "External id": 4722643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359203674.901, "dur": 3.394, + "args": { + "External id": 4722644,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359203676.599, "dur": 1.526, + "args": { + "External id": 4722645,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 8300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359203679.701, "dur": 51.554, + "args": { + "External id": 4722646,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[23068672, 5632, 1], [1, 5632]], "Input Dims": [[16, 4096, 5632], [5632, 2048]], "Ev Idx": 8301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359203683.417, "dur": 2.681, + "args": { + "External id": 4722647,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203684.203, "dur": 1.788, + "args": { + "External id": 4722648,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359203686.591, "dur": 40.961, + "args": { + "External id": 4722649,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 8304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203729.555, "dur": 1.054, + "args": { + "External id": 4722650,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1712359203754.890, "dur": 26.938, + "args": { + "External id": 4722651,"Sequence number": 47018855, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 8306 + } + }, + { + "ph": "s", "id": 137, "pid": 1336753, "tid": 1336753, "ts": 1712359203754.890, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359203815.006, "dur": 212.788, + "args": { + "External id": 4722652,"Sequence number": 47018856, "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": [[8388608, 2048, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [], [], [], [], []], "Ev Idx": 8307 + } + }, + { + "ph": "s", "id": 136, "pid": 1336753, "tid": 1336753, "ts": 1712359203815.006, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359203833.201, "dur": 5.362, + "args": { + "External id": 4722653,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203836.542, "dur": 1.852, + "args": { + "External id": 4722654,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359203845.623, "dur": 6.439, + "args": { + "External id": 4722655,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359203847.896, "dur": 3.775, + "args": { + "External id": 4722656,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359203857.344, "dur": 3.727, + "args": { + "External id": 4722657,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359203973.591, "dur": 3.233, + "args": { + "External id": 4722658,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359203974.557, "dur": 2.040, + "args": { + "External id": 4722659,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359204050.774, "dur": 119.141, + "args": { + "External id": 4722660,"Sequence number": 47018857, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359204051.847, "dur": 10.910, + "args": { + "External id": 4722661,"Sequence number": 47018857, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8316 + } + }, + { + "ph": "s", "id": 135, "pid": 1336753, "tid": 1336753, "ts": 1712359204051.847, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359204056.865, "dur": 4.321, + "args": { + "External id": 4722662,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359204058.981, "dur": 1.832, + "args": { + "External id": 4722663,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359204076.934, "dur": 92.631, + "args": { + "External id": 4722664,"Sequence number": 47018858, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359204079.168, "dur": 7.523, + "args": { + "External id": 4722665,"Sequence number": 47018858, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204082.496, "dur": 3.965, + "args": { + "External id": 4722666,"Sequence number": 47018858, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8321 + } + }, + { + "ph": "s", "id": 134, "pid": 1336753, "tid": 1336753, "ts": 1712359204082.496, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359204087.561, "dur": 75.636, + "args": { + "External id": 4722667,"Sequence number": 47018859, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8322 + } + }, + { + "ph": "s", "id": 133, "pid": 1336753, "tid": 1336753, "ts": 1712359204087.561, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204165.690, "dur": 3.098, + "args": { + "External id": 4722668,"Sequence number": 47018860, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8323 + } + }, + { + "ph": "s", "id": 132, "pid": 1336753, "tid": 1336753, "ts": 1712359204165.690, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359204180.620, "dur": 70.346, + "args": { + "External id": 4722669,"Sequence number": 47018861, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359204181.486, "dur": 11.241, + "args": { + "External id": 4722670,"Sequence number": 47018861, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8325 + } + }, + { + "ph": "s", "id": 131, "pid": 1336753, "tid": 1336753, "ts": 1712359204181.486, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359204188.269, "dur": 2.943, + "args": { + "External id": 4722671,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359204189.903, "dur": 1.157, + "args": { + "External id": 4722672,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359204193.630, "dur": 57.150, + "args": { + "External id": 4722673,"Sequence number": 47018862, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359204194.723, "dur": 4.703, + "args": { + "External id": 4722674,"Sequence number": 47018862, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204195.494, "dur": 3.819, + "args": { + "External id": 4722675,"Sequence number": 47018862, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8330 + } + }, + { + "ph": "s", "id": 130, "pid": 1336753, "tid": 1336753, "ts": 1712359204195.494, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359204199.899, "dur": 46.352, + "args": { + "External id": 4722676,"Sequence number": 47018863, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8331 + } + }, + { + "ph": "s", "id": 129, "pid": 1336753, "tid": 1336753, "ts": 1712359204199.899, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204248.026, "dur": 2.421, + "args": { + "External id": 4722677,"Sequence number": 47018864, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8332 + } + }, + { + "ph": "s", "id": 128, "pid": 1336753, "tid": 1336753, "ts": 1712359204248.026, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359204258.057, "dur": 64.571, + "args": { + "External id": 4722678,"Sequence number": 47018865, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359204258.823, "dur": 9.329, + "args": { + "External id": 4722679,"Sequence number": 47018865, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8334 + } + }, + { + "ph": "s", "id": 127, "pid": 1336753, "tid": 1336753, "ts": 1712359204258.823, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359204260.485, "dur": 6.606, + "args": { + "External id": 4722680,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359204264.182, "dur": 2.734, + "args": { + "External id": 4722681,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359204268.920, "dur": 53.505, + "args": { + "External id": 4722682,"Sequence number": 47018866, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359204270.302, "dur": 4.494, + "args": { + "External id": 4722683,"Sequence number": 47018866, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204271.407, "dur": 3.242, + "args": { + "External id": 4722684,"Sequence number": 47018866, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8339 + } + }, + { + "ph": "s", "id": 126, "pid": 1336753, "tid": 1336753, "ts": 1712359204271.407, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359204277.295, "dur": 38.740, + "args": { + "External id": 4722685,"Sequence number": 47018867, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8340 + } + }, + { + "ph": "s", "id": 125, "pid": 1336753, "tid": 1336753, "ts": 1712359204277.295, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204317.936, "dur": 4.113, + "args": { + "External id": 4722686,"Sequence number": 47018868, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8341 + } + }, + { + "ph": "s", "id": 124, "pid": 1336753, "tid": 1336753, "ts": 1712359204317.936, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359204338.547, "dur": 4.442, + "args": { + "External id": 4722687,"Sequence number": 47018869, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204339.579, "dur": 3.276, + "args": { + "External id": 4722688,"Sequence number": 47018869, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8343 + } + }, + { + "ph": "s", "id": 123, "pid": 1336753, "tid": 1336753, "ts": 1712359204339.579, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359204427.950, "dur": 9.353, + "args": { + "External id": 4722689,"Sequence number": 47018870, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204432.568, "dur": 4.597, + "args": { + "External id": 4722690,"Sequence number": 47018870, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8345 + } + }, + { + "ph": "s", "id": 122, "pid": 1336753, "tid": 1336753, "ts": 1712359204432.568, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359204442.579, "dur": 5.161, + "args": { + "External id": 4722691,"Sequence number": 47018871, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204443.573, "dur": 4.010, + "args": { + "External id": 4722692,"Sequence number": 47018871, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8347 + } + }, + { + "ph": "s", "id": 121, "pid": 1336753, "tid": 1336753, "ts": 1712359204443.573, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359204478.987, "dur": 169.278, + "args": { + "External id": 4722693,"Sequence number": 47018872, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8348 + } + }, + { + "ph": "s", "id": 120, "pid": 1336753, "tid": 1336753, "ts": 1712359204478.987, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359204498.273, "dur": 9.238, + "args": { + "External id": 4722694,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359204501.367, "dur": 5.566, + "args": { + "External id": 4722695,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359204662.466, "dur": 98.581, + "args": { + "External id": 4722696,"Sequence number": 47018873, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8351 + } + }, + { + "ph": "s", "id": 119, "pid": 1336753, "tid": 1336753, "ts": 1712359204662.466, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359204675.273, "dur": 6.600, + "args": { + "External id": 4722697,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359204677.794, "dur": 3.650, + "args": { + "External id": 4722698,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336753, "tid": 1336753, + "ts": 1712359204786.812, "dur": 177.941, + "args": { + "External id": 4722699,"Sequence number": 47018874, "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 8354 + } + }, + { + "ph": "s", "id": 118, "pid": 1336753, "tid": 1336753, "ts": 1712359204786.812, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359204816.083, "dur": 124.417, + "args": { + "External id": 4722700,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359204865.281, "dur": 6.946, + "args": { + "External id": 4722701,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359204867.594, "dur": 4.200, + "args": { + "External id": 4722702,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359204874.672, "dur": 4.200, + "args": { + "External id": 4722703,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359204879.932, "dur": 3.444, + "args": { + "External id": 4722704,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359204885.830, "dur": 4.170, + "args": { + "External id": 4722705,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1712359204951.564, "dur": 4.222, + "args": { + "External id": 4722706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359204969.582, "dur": 6.740, + "args": { + "External id": 4722707,"Sequence number": 47018875, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359204970.682, "dur": 5.513, + "args": { + "External id": 4722708,"Sequence number": 47018875, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8363 + } + }, + { + "ph": "s", "id": 117, "pid": 1336753, "tid": 1336753, "ts": 1712359204970.682, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359205031.043, "dur": 132.546, + "args": { + "External id": 4722709,"Sequence number": 47018876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359205032.362, "dur": 10.277, + "args": { + "External id": 4722710,"Sequence number": 47018876, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8365 + } + }, + { + "ph": "s", "id": 116, "pid": 1336753, "tid": 1336753, "ts": 1712359205032.362, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359205035.898, "dur": 4.928, + "args": { + "External id": 4722711,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359205038.409, "dur": 1.975, + "args": { + "External id": 4722712,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359205043.927, "dur": 119.369, + "args": { + "External id": 4722713,"Sequence number": 47018877, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205047.767, "dur": 5.666, + "args": { + "External id": 4722714,"Sequence number": 47018877, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205048.266, "dur": 4.959, + "args": { + "External id": 4722715,"Sequence number": 47018877, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8370 + } + }, + { + "ph": "s", "id": 115, "pid": 1336753, "tid": 1336753, "ts": 1712359205048.266, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359205054.330, "dur": 98.656, + "args": { + "External id": 4722716,"Sequence number": 47018878, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8371 + } + }, + { + "ph": "s", "id": 114, "pid": 1336753, "tid": 1336753, "ts": 1712359205054.330, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205156.403, "dur": 6.095, + "args": { + "External id": 4722717,"Sequence number": 47018879, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8372 + } + }, + { + "ph": "s", "id": 113, "pid": 1336753, "tid": 1336753, "ts": 1712359205156.403, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359205201.132, "dur": 213.463, + "args": { + "External id": 4722718,"Sequence number": 47018880, "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": [[8388608, 2048, 1], [1], [], [8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [16, 4096, 2048], [], [], [], []], "Ev Idx": 8373 + } + }, + { + "ph": "s", "id": 112, "pid": 1336753, "tid": 1336753, "ts": 1712359205201.132, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205223.288, "dur": 2.962, + "args": { + "External id": 4722719,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205224.041, "dur": 1.876, + "args": { + "External id": 4722720,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359205230.592, "dur": 5.352, + "args": { + "External id": 4722721,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [2048, 1]], "Input Dims": [[16, 4096, 2048], [65536, 2048]], "Ev Idx": 8376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205231.482, "dur": 4.356, + "args": { + "External id": 4722722,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205234.761, "dur": 0.954, + "args": { + "External id": 4722723,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359205243.412, "dur": 7.484, + "args": { + "External id": 4722724,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359205245.671, "dur": 4.892, + "args": { + "External id": 4722725,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359205257.045, "dur": 3.760, + "args": { + "External id": 4722726,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359205264.503, "dur": 3.677, + "args": { + "External id": 4722727,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205389.611, "dur": 3.221, + "args": { + "External id": 4722728,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205390.741, "dur": 1.879, + "args": { + "External id": 4722729,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205397.486, "dur": 1.810, + "args": { + "External id": 4722730,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205398.375, "dur": 0.814, + "args": { + "External id": 4722731,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359205433.567, "dur": 91.803, + "args": { + "External id": 4722732,"Sequence number": 47018881, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359205434.651, "dur": 7.671, + "args": { + "External id": 4722733,"Sequence number": 47018881, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8388 + } + }, + { + "ph": "s", "id": 111, "pid": 1336753, "tid": 1336753, "ts": 1712359205434.651, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359205437.196, "dur": 3.915, + "args": { + "External id": 4722734,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359205439.251, "dur": 1.607, + "args": { + "External id": 4722735,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359205445.625, "dur": 79.489, + "args": { + "External id": 4722736,"Sequence number": 47018882, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205447.142, "dur": 2.664, + "args": { + "External id": 4722737,"Sequence number": 47018882, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205447.942, "dur": 1.676, + "args": { + "External id": 4722738,"Sequence number": 47018882, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8393 + } + }, + { + "ph": "s", "id": 110, "pid": 1336753, "tid": 1336753, "ts": 1712359205447.942, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359205450.617, "dur": 67.346, + "args": { + "External id": 4722739,"Sequence number": 47018883, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8394 + } + }, + { + "ph": "s", "id": 109, "pid": 1336753, "tid": 1336753, "ts": 1712359205450.617, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205520.000, "dur": 4.476, + "args": { + "External id": 4722740,"Sequence number": 47018884, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8395 + } + }, + { + "ph": "s", "id": 108, "pid": 1336753, "tid": 1336753, "ts": 1712359205520.000, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359205533.535, "dur": 68.168, + "args": { + "External id": 4722741,"Sequence number": 47018885, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359205534.181, "dur": 6.037, + "args": { + "External id": 4722742,"Sequence number": 47018885, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8397 + } + }, + { + "ph": "s", "id": 107, "pid": 1336753, "tid": 1336753, "ts": 1712359205534.181, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359205536.662, "dur": 2.392, + "args": { + "External id": 4722743,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359205538.030, "dur": 0.866, + "args": { + "External id": 4722744,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359205540.953, "dur": 60.510, + "args": { + "External id": 4722745,"Sequence number": 47018886, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205544.414, "dur": 6.200, + "args": { + "External id": 4722746,"Sequence number": 47018886, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205545.052, "dur": 5.391, + "args": { + "External id": 4722747,"Sequence number": 47018886, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8402 + } + }, + { + "ph": "s", "id": 106, "pid": 1336753, "tid": 1336753, "ts": 1712359205545.052, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359205551.296, "dur": 44.207, + "args": { + "External id": 4722748,"Sequence number": 47018887, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8403 + } + }, + { + "ph": "s", "id": 105, "pid": 1336753, "tid": 1336753, "ts": 1712359205551.296, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205596.991, "dur": 4.116, + "args": { + "External id": 4722749,"Sequence number": 47018888, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8404 + } + }, + { + "ph": "s", "id": 104, "pid": 1336753, "tid": 1336753, "ts": 1712359205596.991, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359205623.650, "dur": 138.950, + "args": { + "External id": 4722750,"Sequence number": 47018889, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8405 + } + }, + { + "ph": "s", "id": 103, "pid": 1336753, "tid": 1336753, "ts": 1712359205623.650, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359205659.116, "dur": 3.965, + "args": { + "External id": 4722751,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359205693.859, "dur": 55.903, + "args": { + "External id": 4722752,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359205694.651, "dur": 4.638, + "args": { + "External id": 4722753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359205695.674, "dur": 2.798, + "args": { + "External id": 4722754,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359205697.339, "dur": 0.927, + "args": { + "External id": 4722755,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 8410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359205702.250, "dur": 47.116, + "args": { + "External id": 4722756,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[23068672, 5632, 1], [1, 5632]], "Input Dims": [[16, 4096, 5632], [5632, 2048]], "Ev Idx": 8411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205703.558, "dur": 2.252, + "args": { + "External id": 4722757,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205704.368, "dur": 1.336, + "args": { + "External id": 4722758,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359205706.345, "dur": 39.598, + "args": { + "External id": 4722759,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 8414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205747.651, "dur": 1.037, + "args": { + "External id": 4722760,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1712359205770.362, "dur": 24.778, + "args": { + "External id": 4722761,"Sequence number": 47018890, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 8416 + } + }, + { + "ph": "s", "id": 102, "pid": 1336753, "tid": 1336753, "ts": 1712359205770.362, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359205825.248, "dur": 199.549, + "args": { + "External id": 4722762,"Sequence number": 47018891, "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": [[8388608, 2048, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [], [], [], [], []], "Ev Idx": 8417 + } + }, + { + "ph": "s", "id": 101, "pid": 1336753, "tid": 1336753, "ts": 1712359205825.248, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205843.261, "dur": 2.747, + "args": { + "External id": 4722763,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205844.133, "dur": 1.542, + "args": { + "External id": 4722764,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359205853.044, "dur": 6.136, + "args": { + "External id": 4722765,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359205855.004, "dur": 3.806, + "args": { + "External id": 4722766,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359205864.196, "dur": 3.212, + "args": { + "External id": 4722767,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359205968.669, "dur": 2.940, + "args": { + "External id": 4722768,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359205969.642, "dur": 1.786, + "args": { + "External id": 4722769,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359206047.339, "dur": 112.807, + "args": { + "External id": 4722770,"Sequence number": 47018892, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359206048.235, "dur": 8.330, + "args": { + "External id": 4722771,"Sequence number": 47018892, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8426 + } + }, + { + "ph": "s", "id": 100, "pid": 1336753, "tid": 1336753, "ts": 1712359206048.235, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359206050.822, "dur": 4.094, + "args": { + "External id": 4722772,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359206053.334, "dur": 1.342, + "args": { + "External id": 4722773,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359206057.387, "dur": 102.261, + "args": { + "External id": 4722774,"Sequence number": 47018893, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359206060.958, "dur": 18.674, + "args": { + "External id": 4722775,"Sequence number": 47018893, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206061.631, "dur": 17.517, + "args": { + "External id": 4722776,"Sequence number": 47018893, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8431 + } + }, + { + "ph": "s", "id": 99, "pid": 1336753, "tid": 1336753, "ts": 1712359206061.631, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359206081.153, "dur": 70.824, + "args": { + "External id": 4722777,"Sequence number": 47018894, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8432 + } + }, + { + "ph": "s", "id": 98, "pid": 1336753, "tid": 1336753, "ts": 1712359206081.153, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206154.147, "dur": 4.815, + "args": { + "External id": 4722778,"Sequence number": 47018895, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8433 + } + }, + { + "ph": "s", "id": 97, "pid": 1336753, "tid": 1336753, "ts": 1712359206154.147, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359206170.444, "dur": 63.953, + "args": { + "External id": 4722779,"Sequence number": 47018896, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359206173.518, "dur": 6.273, + "args": { + "External id": 4722780,"Sequence number": 47018896, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8435 + } + }, + { + "ph": "s", "id": 96, "pid": 1336753, "tid": 1336753, "ts": 1712359206173.518, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359206175.375, "dur": 3.020, + "args": { + "External id": 4722781,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359206177.143, "dur": 1.110, + "args": { + "External id": 4722782,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359206180.568, "dur": 53.566, + "args": { + "External id": 4722783,"Sequence number": 47018897, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359206181.450, "dur": 5.301, + "args": { + "External id": 4722784,"Sequence number": 47018897, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206184.307, "dur": 2.319, + "args": { + "External id": 4722785,"Sequence number": 47018897, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8440 + } + }, + { + "ph": "s", "id": 95, "pid": 1336753, "tid": 1336753, "ts": 1712359206184.307, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359206187.455, "dur": 42.623, + "args": { + "External id": 4722786,"Sequence number": 47018898, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8441 + } + }, + { + "ph": "s", "id": 94, "pid": 1336753, "tid": 1336753, "ts": 1712359206187.455, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206231.604, "dur": 2.247, + "args": { + "External id": 4722787,"Sequence number": 47018899, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8442 + } + }, + { + "ph": "s", "id": 93, "pid": 1336753, "tid": 1336753, "ts": 1712359206231.604, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359206240.876, "dur": 61.973, + "args": { + "External id": 4722788,"Sequence number": 47018900, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359206241.375, "dur": 9.218, + "args": { + "External id": 4722789,"Sequence number": 47018900, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8444 + } + }, + { + "ph": "s", "id": 92, "pid": 1336753, "tid": 1336753, "ts": 1712359206241.375, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359206245.205, "dur": 4.205, + "args": { + "External id": 4722790,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359206246.536, "dur": 2.688, + "args": { + "External id": 4722791,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359206251.116, "dur": 51.440, + "args": { + "External id": 4722792,"Sequence number": 47018901, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359206252.265, "dur": 6.252, + "args": { + "External id": 4722793,"Sequence number": 47018901, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206255.171, "dur": 3.220, + "args": { + "External id": 4722794,"Sequence number": 47018901, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8449 + } + }, + { + "ph": "s", "id": 91, "pid": 1336753, "tid": 1336753, "ts": 1712359206255.171, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359206259.005, "dur": 36.653, + "args": { + "External id": 4722795,"Sequence number": 47018902, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8450 + } + }, + { + "ph": "s", "id": 90, "pid": 1336753, "tid": 1336753, "ts": 1712359206259.005, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206297.075, "dur": 5.155, + "args": { + "External id": 4722796,"Sequence number": 47018903, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8451 + } + }, + { + "ph": "s", "id": 89, "pid": 1336753, "tid": 1336753, "ts": 1712359206297.075, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359206317.747, "dur": 5.597, + "args": { + "External id": 4722797,"Sequence number": 47018904, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206318.531, "dur": 4.427, + "args": { + "External id": 4722798,"Sequence number": 47018904, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8453 + } + }, + { + "ph": "s", "id": 88, "pid": 1336753, "tid": 1336753, "ts": 1712359206318.531, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359206329.843, "dur": 3.042, + "args": { + "External id": 4722799,"Sequence number": 47018905, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206330.788, "dur": 1.965, + "args": { + "External id": 4722800,"Sequence number": 47018905, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8455 + } + }, + { + "ph": "s", "id": 87, "pid": 1336753, "tid": 1336753, "ts": 1712359206330.788, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359206337.080, "dur": 2.826, + "args": { + "External id": 4722801,"Sequence number": 47018906, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206337.967, "dur": 1.813, + "args": { + "External id": 4722802,"Sequence number": 47018906, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8457 + } + }, + { + "ph": "s", "id": 86, "pid": 1336753, "tid": 1336753, "ts": 1712359206337.967, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359206368.053, "dur": 146.351, + "args": { + "External id": 4722803,"Sequence number": 47018907, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8458 + } + }, + { + "ph": "s", "id": 85, "pid": 1336753, "tid": 1336753, "ts": 1712359206368.053, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359206386.783, "dur": 10.095, + "args": { + "External id": 4722804,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359206389.206, "dur": 7.256, + "args": { + "External id": 4722805,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359206525.524, "dur": 102.433, + "args": { + "External id": 4722806,"Sequence number": 47018908, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8461 + } + }, + { + "ph": "s", "id": 84, "pid": 1336753, "tid": 1336753, "ts": 1712359206525.524, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359206537.416, "dur": 6.334, + "args": { + "External id": 4722807,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359206539.662, "dur": 3.739, + "args": { + "External id": 4722808,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336753, "tid": 1336753, + "ts": 1712359206655.920, "dur": 177.027, + "args": { + "External id": 4722809,"Sequence number": 47018909, "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 8464 + } + }, + { + "ph": "s", "id": 83, "pid": 1336753, "tid": 1336753, "ts": 1712359206655.920, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359206681.544, "dur": 126.359, + "args": { + "External id": 4722810,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359206730.217, "dur": 7.135, + "args": { + "External id": 4722811,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359206732.720, "dur": 4.048, + "args": { + "External id": 4722812,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359206739.775, "dur": 4.080, + "args": { + "External id": 4722813,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359206745.240, "dur": 1.820, + "args": { + "External id": 4722814,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359206749.578, "dur": 3.650, + "args": { + "External id": 4722815,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1712359206819.398, "dur": 4.077, + "args": { + "External id": 4722816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359206838.120, "dur": 4.758, + "args": { + "External id": 4722817,"Sequence number": 47018910, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206839.357, "dur": 3.386, + "args": { + "External id": 4722818,"Sequence number": 47018910, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8473 + } + }, + { + "ph": "s", "id": 82, "pid": 1336753, "tid": 1336753, "ts": 1712359206839.357, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359206854.047, "dur": 100.656, + "args": { + "External id": 4722819,"Sequence number": 47018911, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359206855.066, "dur": 12.432, + "args": { + "External id": 4722820,"Sequence number": 47018911, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8475 + } + }, + { + "ph": "s", "id": 81, "pid": 1336753, "tid": 1336753, "ts": 1712359206855.066, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359206860.068, "dur": 6.171, + "args": { + "External id": 4722821,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359206864.563, "dur": 1.413, + "args": { + "External id": 4722822,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359206868.661, "dur": 85.732, + "args": { + "External id": 4722823,"Sequence number": 47018912, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359206869.956, "dur": 2.851, + "args": { + "External id": 4722824,"Sequence number": 47018912, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206870.575, "dur": 2.115, + "args": { + "External id": 4722825,"Sequence number": 47018912, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8480 + } + }, + { + "ph": "s", "id": 80, "pid": 1336753, "tid": 1336753, "ts": 1712359206870.575, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359206873.526, "dur": 72.715, + "args": { + "External id": 4722826,"Sequence number": 47018913, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8481 + } + }, + { + "ph": "s", "id": 79, "pid": 1336753, "tid": 1336753, "ts": 1712359206873.526, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359206948.310, "dur": 5.559, + "args": { + "External id": 4722827,"Sequence number": 47018914, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8482 + } + }, + { + "ph": "s", "id": 78, "pid": 1336753, "tid": 1336753, "ts": 1712359206948.310, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359207028.263, "dur": 241.600, + "args": { + "External id": 4722828,"Sequence number": 47018915, "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": [[8388608, 2048, 1], [1], [], [8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [16, 4096, 2048], [], [], [], []], "Ev Idx": 8483 + } + }, + { + "ph": "s", "id": 77, "pid": 1336753, "tid": 1336753, "ts": 1712359207028.263, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207048.794, "dur": 4.178, + "args": { + "External id": 4722829,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207049.981, "dur": 2.623, + "args": { + "External id": 4722830,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359207056.991, "dur": 5.446, + "args": { + "External id": 4722831,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [2048, 1]], "Input Dims": [[16, 4096, 2048], [65536, 2048]], "Ev Idx": 8486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207060.484, "dur": 1.853, + "args": { + "External id": 4722832,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207061.066, "dur": 1.151, + "args": { + "External id": 4722833,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359207085.096, "dur": 9.772, + "args": { + "External id": 4722834,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359207087.544, "dur": 6.579, + "args": { + "External id": 4722835,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359207101.978, "dur": 4.119, + "args": { + "External id": 4722836,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359207109.451, "dur": 4.134, + "args": { + "External id": 4722837,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207245.539, "dur": 3.992, + "args": { + "External id": 4722838,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207246.404, "dur": 2.917, + "args": { + "External id": 4722839,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207252.227, "dur": 1.834, + "args": { + "External id": 4722840,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207253.071, "dur": 0.886, + "args": { + "External id": 4722841,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359207290.375, "dur": 130.140, + "args": { + "External id": 4722842,"Sequence number": 47018916, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359207301.601, "dur": 10.238, + "args": { + "External id": 4722843,"Sequence number": 47018916, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8498 + } + }, + { + "ph": "s", "id": 76, "pid": 1336753, "tid": 1336753, "ts": 1712359207301.601, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359207306.726, "dur": 3.318, + "args": { + "External id": 4722844,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359207308.386, "dur": 1.390, + "args": { + "External id": 4722845,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359207312.967, "dur": 107.253, + "args": { + "External id": 4722846,"Sequence number": 47018917, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207314.402, "dur": 6.865, + "args": { + "External id": 4722847,"Sequence number": 47018917, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207315.033, "dur": 6.050, + "args": { + "External id": 4722848,"Sequence number": 47018917, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8503 + } + }, + { + "ph": "s", "id": 75, "pid": 1336753, "tid": 1336753, "ts": 1712359207315.033, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359207322.162, "dur": 89.265, + "args": { + "External id": 4722849,"Sequence number": 47018918, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8504 + } + }, + { + "ph": "s", "id": 74, "pid": 1336753, "tid": 1336753, "ts": 1712359207322.162, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207413.380, "dur": 6.135, + "args": { + "External id": 4722850,"Sequence number": 47018919, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8505 + } + }, + { + "ph": "s", "id": 73, "pid": 1336753, "tid": 1336753, "ts": 1712359207413.380, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359207428.324, "dur": 88.388, + "args": { + "External id": 4722851,"Sequence number": 47018920, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359207428.942, "dur": 7.232, + "args": { + "External id": 4722852,"Sequence number": 47018920, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8507 + } + }, + { + "ph": "s", "id": 72, "pid": 1336753, "tid": 1336753, "ts": 1712359207428.942, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359207430.204, "dur": 4.847, + "args": { + "External id": 4722853,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359207433.872, "dur": 0.935, + "args": { + "External id": 4722854,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359207436.879, "dur": 79.611, + "args": { + "External id": 4722855,"Sequence number": 47018921, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207437.902, "dur": 4.755, + "args": { + "External id": 4722856,"Sequence number": 47018921, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207438.658, "dur": 3.869, + "args": { + "External id": 4722857,"Sequence number": 47018921, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8512 + } + }, + { + "ph": "s", "id": 71, "pid": 1336753, "tid": 1336753, "ts": 1712359207438.658, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359207445.395, "dur": 66.537, + "args": { + "External id": 4722858,"Sequence number": 47018922, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8513 + } + }, + { + "ph": "s", "id": 70, "pid": 1336753, "tid": 1336753, "ts": 1712359207445.395, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207513.721, "dur": 2.427, + "args": { + "External id": 4722859,"Sequence number": 47018923, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8514 + } + }, + { + "ph": "s", "id": 69, "pid": 1336753, "tid": 1336753, "ts": 1712359207513.721, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359207538.428, "dur": 142.193, + "args": { + "External id": 4722860,"Sequence number": 47018924, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8515 + } + }, + { + "ph": "s", "id": 68, "pid": 1336753, "tid": 1336753, "ts": 1712359207538.428, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359207573.316, "dur": 4.134, + "args": { + "External id": 4722861,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359207609.819, "dur": 58.550, + "args": { + "External id": 4722862,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359207610.435, "dur": 4.372, + "args": { + "External id": 4722863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359207611.479, "dur": 2.491, + "args": { + "External id": 4722864,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359207613.090, "dur": 0.633, + "args": { + "External id": 4722865,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 8520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359207615.426, "dur": 52.555, + "args": { + "External id": 4722866,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[23068672, 5632, 1], [1, 5632]], "Input Dims": [[16, 4096, 5632], [5632, 2048]], "Ev Idx": 8521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207617.250, "dur": 2.184, + "args": { + "External id": 4722867,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207617.853, "dur": 1.461, + "args": { + "External id": 4722868,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359207622.163, "dur": 42.172, + "args": { + "External id": 4722869,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 8524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207666.276, "dur": 1.090, + "args": { + "External id": 4722870,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1712359207688.639, "dur": 25.918, + "args": { + "External id": 4722871,"Sequence number": 47018925, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 8526 + } + }, + { + "ph": "s", "id": 67, "pid": 1336753, "tid": 1336753, "ts": 1712359207688.639, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359207747.405, "dur": 190.962, + "args": { + "External id": 4722872,"Sequence number": 47018926, "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": [[8388608, 2048, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [], [], [], [], []], "Ev Idx": 8527 + } + }, + { + "ph": "s", "id": 66, "pid": 1336753, "tid": 1336753, "ts": 1712359207747.405, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207763.715, "dur": 3.229, + "args": { + "External id": 4722873,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207764.637, "dur": 2.173, + "args": { + "External id": 4722874,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359207776.722, "dur": 9.662, + "args": { + "External id": 4722875,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359207781.440, "dur": 4.561, + "args": { + "External id": 4722876,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359207810.275, "dur": 6.125, + "args": { + "External id": 4722877,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207926.223, "dur": 3.232, + "args": { + "External id": 4722878,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207927.393, "dur": 1.700, + "args": { + "External id": 4722879,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359207956.565, "dur": 147.737, + "args": { + "External id": 4722880,"Sequence number": 47018927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359207957.536, "dur": 8.827, + "args": { + "External id": 4722881,"Sequence number": 47018927, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8536 + } + }, + { + "ph": "s", "id": 65, "pid": 1336753, "tid": 1336753, "ts": 1712359207957.536, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359207959.808, "dur": 5.304, + "args": { + "External id": 4722882,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359207963.680, "dur": 1.194, + "args": { + "External id": 4722883,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359207967.066, "dur": 136.919, + "args": { + "External id": 4722884,"Sequence number": 47018928, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359207968.112, "dur": 4.005, + "args": { + "External id": 4722885,"Sequence number": 47018928, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359207968.805, "dur": 3.167, + "args": { + "External id": 4722886,"Sequence number": 47018928, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8541 + } + }, + { + "ph": "s", "id": 64, "pid": 1336753, "tid": 1336753, "ts": 1712359207968.805, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359207975.250, "dur": 120.351, + "args": { + "External id": 4722887,"Sequence number": 47018929, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8542 + } + }, + { + "ph": "s", "id": 63, "pid": 1336753, "tid": 1336753, "ts": 1712359207975.250, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208099.388, "dur": 3.795, + "args": { + "External id": 4722888,"Sequence number": 47018930, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8543 + } + }, + { + "ph": "s", "id": 62, "pid": 1336753, "tid": 1336753, "ts": 1712359208099.388, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359208114.756, "dur": 71.472, + "args": { + "External id": 4722889,"Sequence number": 47018931, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359208115.586, "dur": 10.729, + "args": { + "External id": 4722890,"Sequence number": 47018931, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8545 + } + }, + { + "ph": "s", "id": 61, "pid": 1336753, "tid": 1336753, "ts": 1712359208115.586, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359208117.350, "dur": 7.627, + "args": { + "External id": 4722891,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359208121.371, "dur": 3.219, + "args": { + "External id": 4722892,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359208127.311, "dur": 58.655, + "args": { + "External id": 4722893,"Sequence number": 47018932, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359208128.507, "dur": 2.903, + "args": { + "External id": 4722894,"Sequence number": 47018932, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208129.007, "dur": 2.286, + "args": { + "External id": 4722895,"Sequence number": 47018932, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8550 + } + }, + { + "ph": "s", "id": 60, "pid": 1336753, "tid": 1336753, "ts": 1712359208129.007, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359208132.015, "dur": 47.058, + "args": { + "External id": 4722896,"Sequence number": 47018933, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8551 + } + }, + { + "ph": "s", "id": 59, "pid": 1336753, "tid": 1336753, "ts": 1712359208132.015, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208180.623, "dur": 4.968, + "args": { + "External id": 4722897,"Sequence number": 47018934, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8552 + } + }, + { + "ph": "s", "id": 58, "pid": 1336753, "tid": 1336753, "ts": 1712359208180.623, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359208193.266, "dur": 61.996, + "args": { + "External id": 4722898,"Sequence number": 47018935, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359208193.714, "dur": 5.732, + "args": { + "External id": 4722899,"Sequence number": 47018935, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8554 + } + }, + { + "ph": "s", "id": 57, "pid": 1336753, "tid": 1336753, "ts": 1712359208193.714, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359208195.539, "dur": 2.444, + "args": { + "External id": 4722900,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359208197.188, "dur": 0.658, + "args": { + "External id": 4722901,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359208202.460, "dur": 52.591, + "args": { + "External id": 4722902,"Sequence number": 47018936, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359208203.541, "dur": 5.026, + "args": { + "External id": 4722903,"Sequence number": 47018936, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208204.601, "dur": 3.830, + "args": { + "External id": 4722904,"Sequence number": 47018936, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8559 + } + }, + { + "ph": "s", "id": 56, "pid": 1336753, "tid": 1336753, "ts": 1712359208204.601, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359208209.117, "dur": 39.327, + "args": { + "External id": 4722905,"Sequence number": 47018937, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8560 + } + }, + { + "ph": "s", "id": 55, "pid": 1336753, "tid": 1336753, "ts": 1712359208209.117, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208250.113, "dur": 4.660, + "args": { + "External id": 4722906,"Sequence number": 47018938, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8561 + } + }, + { + "ph": "s", "id": 54, "pid": 1336753, "tid": 1336753, "ts": 1712359208250.113, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359208270.401, "dur": 4.440, + "args": { + "External id": 4722907,"Sequence number": 47018939, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208271.284, "dur": 3.379, + "args": { + "External id": 4722908,"Sequence number": 47018939, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8563 + } + }, + { + "ph": "s", "id": 53, "pid": 1336753, "tid": 1336753, "ts": 1712359208271.284, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359208281.218, "dur": 3.319, + "args": { + "External id": 4722909,"Sequence number": 47018940, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208282.330, "dur": 2.086, + "args": { + "External id": 4722910,"Sequence number": 47018940, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8565 + } + }, + { + "ph": "s", "id": 52, "pid": 1336753, "tid": 1336753, "ts": 1712359208282.330, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359208291.016, "dur": 5.982, + "args": { + "External id": 4722911,"Sequence number": 47018941, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208292.052, "dur": 4.786, + "args": { + "External id": 4722912,"Sequence number": 47018941, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8567 + } + }, + { + "ph": "s", "id": 51, "pid": 1336753, "tid": 1336753, "ts": 1712359208292.052, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359208325.269, "dur": 144.442, + "args": { + "External id": 4722913,"Sequence number": 47018942, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8568 + } + }, + { + "ph": "s", "id": 50, "pid": 1336753, "tid": 1336753, "ts": 1712359208325.269, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359208343.140, "dur": 8.513, + "args": { + "External id": 4722914,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359208346.180, "dur": 5.017, + "args": { + "External id": 4722915,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359208482.027, "dur": 100.108, + "args": { + "External id": 4722916,"Sequence number": 47018943, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8571 + } + }, + { + "ph": "s", "id": 49, "pid": 1336753, "tid": 1336753, "ts": 1712359208482.027, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359208495.262, "dur": 6.817, + "args": { + "External id": 4722917,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359208497.485, "dur": 4.224, + "args": { + "External id": 4722918,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336753, "tid": 1336753, + "ts": 1712359208606.950, "dur": 173.994, + "args": { + "External id": 4722919,"Sequence number": 47018944, "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": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 8574 + } + }, + { + "ph": "s", "id": 48, "pid": 1336753, "tid": 1336753, "ts": 1712359208606.950, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359208633.171, "dur": 123.389, + "args": { + "External id": 4722920,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359208681.677, "dur": 7.842, + "args": { + "External id": 4722921,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359208684.223, "dur": 4.853, + "args": { + "External id": 4722922,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359208691.947, "dur": 3.856, + "args": { + "External id": 4722923,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359208696.813, "dur": 3.263, + "args": { + "External id": 4722924,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359208702.834, "dur": 3.452, + "args": { + "External id": 4722925,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1712359208767.253, "dur": 4.020, + "args": { + "External id": 4722926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359208786.262, "dur": 5.074, + "args": { + "External id": 4722927,"Sequence number": 47018945, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208787.439, "dur": 3.777, + "args": { + "External id": 4722928,"Sequence number": 47018945, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8583 + } + }, + { + "ph": "s", "id": 47, "pid": 1336753, "tid": 1336753, "ts": 1712359208787.439, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359208802.364, "dur": 92.056, + "args": { + "External id": 4722929,"Sequence number": 47018946, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359208805.811, "dur": 6.722, + "args": { + "External id": 4722930,"Sequence number": 47018946, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8585 + } + }, + { + "ph": "s", "id": 46, "pid": 1336753, "tid": 1336753, "ts": 1712359208805.811, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359208808.033, "dur": 3.352, + "args": { + "External id": 4722931,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359208809.867, "dur": 1.242, + "args": { + "External id": 4722932,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359208813.521, "dur": 80.661, + "args": { + "External id": 4722933,"Sequence number": 47018947, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359208815.220, "dur": 5.013, + "args": { + "External id": 4722934,"Sequence number": 47018947, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208818.145, "dur": 1.957, + "args": { + "External id": 4722935,"Sequence number": 47018947, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8590 + } + }, + { + "ph": "s", "id": 45, "pid": 1336753, "tid": 1336753, "ts": 1712359208818.145, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359208820.962, "dur": 67.223, + "args": { + "External id": 4722936,"Sequence number": 47018948, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8591 + } + }, + { + "ph": "s", "id": 44, "pid": 1336753, "tid": 1336753, "ts": 1712359208820.962, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208889.972, "dur": 3.587, + "args": { + "External id": 4722937,"Sequence number": 47018949, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8592 + } + }, + { + "ph": "s", "id": 43, "pid": 1336753, "tid": 1336753, "ts": 1712359208889.972, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359208924.712, "dur": 278.474, + "args": { + "External id": 4722938,"Sequence number": 47018950, "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": [[8388608, 2048, 1], [1], [], [8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [16, 4096, 2048], [], [], [], []], "Ev Idx": 8593 + } + }, + { + "ph": "s", "id": 42, "pid": 1336753, "tid": 1336753, "ts": 1712359208924.712, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359208943.882, "dur": 2.726, + "args": { + "External id": 4722939,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208944.803, "dur": 1.640, + "args": { + "External id": 4722940,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336753, "tid": 1336753, + "ts": 1712359208950.123, "dur": 2.987, + "args": { + "External id": 4722941,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [2048, 1]], "Input Dims": [[16, 4096, 2048], [65536, 2048]], "Ev Idx": 8596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359208951.208, "dur": 1.795, + "args": { + "External id": 4722942,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359208951.846, "dur": 1.052, + "args": { + "External id": 4722943,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359208960.247, "dur": 7.953, + "args": { + "External id": 4722944,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359208963.670, "dur": 4.258, + "args": { + "External id": 4722945,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359208973.760, "dur": 3.136, + "args": { + "External id": 4722946,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359208980.046, "dur": 44.069, + "args": { + "External id": 4722947,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359209178.019, "dur": 4.606, + "args": { + "External id": 4722948,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359209179.477, "dur": 2.850, + "args": { + "External id": 4722949,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359209185.597, "dur": 2.139, + "args": { + "External id": 4722950,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359209186.401, "dur": 1.220, + "args": { + "External id": 4722951,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359209223.792, "dur": 99.706, + "args": { + "External id": 4722952,"Sequence number": 47018951, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359209225.089, "dur": 10.087, + "args": { + "External id": 4722953,"Sequence number": 47018951, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8608 + } + }, + { + "ph": "s", "id": 41, "pid": 1336753, "tid": 1336753, "ts": 1712359209225.089, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359209227.595, "dur": 6.177, + "args": { + "External id": 4722954,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359209229.723, "dur": 3.669, + "args": { + "External id": 4722955,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359209236.252, "dur": 86.940, + "args": { + "External id": 4722956,"Sequence number": 47018952, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359209237.862, "dur": 5.961, + "args": { + "External id": 4722957,"Sequence number": 47018952, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359209240.816, "dur": 2.685, + "args": { + "External id": 4722958,"Sequence number": 47018952, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8613 + } + }, + { + "ph": "s", "id": 40, "pid": 1336753, "tid": 1336753, "ts": 1712359209240.816, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359209244.567, "dur": 70.622, + "args": { + "External id": 4722959,"Sequence number": 47018953, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8614 + } + }, + { + "ph": "s", "id": 39, "pid": 1336753, "tid": 1336753, "ts": 1712359209244.567, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359209317.045, "dur": 5.540, + "args": { + "External id": 4722960,"Sequence number": 47018954, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8615 + } + }, + { + "ph": "s", "id": 38, "pid": 1336753, "tid": 1336753, "ts": 1712359209317.045, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359209331.538, "dur": 73.911, + "args": { + "External id": 4722961,"Sequence number": 47018955, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359209332.129, "dur": 9.551, + "args": { + "External id": 4722962,"Sequence number": 47018955, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8617 + } + }, + { + "ph": "s", "id": 37, "pid": 1336753, "tid": 1336753, "ts": 1712359209332.129, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359209337.970, "dur": 2.619, + "args": { + "External id": 4722963,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359209339.506, "dur": 0.930, + "args": { + "External id": 4722964,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359209342.571, "dur": 62.608, + "args": { + "External id": 4722965,"Sequence number": 47018956, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359209343.416, "dur": 7.394, + "args": { + "External id": 4722966,"Sequence number": 47018956, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359209346.591, "dur": 4.100, + "args": { + "External id": 4722967,"Sequence number": 47018956, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8622 + } + }, + { + "ph": "s", "id": 36, "pid": 1336753, "tid": 1336753, "ts": 1712359209346.591, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359209351.303, "dur": 48.836, + "args": { + "External id": 4722968,"Sequence number": 47018957, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8623 + } + }, + { + "ph": "s", "id": 35, "pid": 1336753, "tid": 1336753, "ts": 1712359209351.303, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359209401.640, "dur": 3.199, + "args": { + "External id": 4722969,"Sequence number": 47018958, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8624 + } + }, + { + "ph": "s", "id": 34, "pid": 1336753, "tid": 1336753, "ts": 1712359209401.640, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359209425.593, "dur": 141.374, + "args": { + "External id": 4722970,"Sequence number": 47018959, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8625 + } + }, + { + "ph": "s", "id": 33, "pid": 1336753, "tid": 1336753, "ts": 1712359209425.593, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359209462.793, "dur": 4.726, + "args": { + "External id": 4722971,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359209497.685, "dur": 58.511, + "args": { + "External id": 4722972,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359209498.668, "dur": 7.465, + "args": { + "External id": 4722973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359209499.596, "dur": 5.387, + "args": { + "External id": 4722974,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359209501.678, "dur": 3.135, + "args": { + "External id": 4722975,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 8630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359209506.793, "dur": 49.101, + "args": { + "External id": 4722976,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[23068672, 5632, 1], [1, 5632]], "Input Dims": [[16, 4096, 5632], [5632, 2048]], "Ev Idx": 8631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1712359209508.126, "dur": 4.550, + "args": { + "External id": 4722977,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359209510.949, "dur": 1.606, + "args": { + "External id": 4722978,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359209513.222, "dur": 39.542, + "args": { + "External id": 4722979,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 8634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1712359209554.400, "dur": 0.902, + "args": { + "External id": 4722980,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1712359209575.270, "dur": 24.768, + "args": { + "External id": 4722981,"Sequence number": 47018960, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 8636 + } + }, + { + "ph": "s", "id": 32, "pid": 1336753, "tid": 1336753, "ts": 1712359209575.270, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336753, "tid": 1336753, + "ts": 1712359209617.204, "dur": 46.426, + "args": { + "External id": 4722982,"Sequence number": 47018961, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "-2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[8388608, 2048, 1], [8388608, 2048, 1], [8388608, 2048, 1], [8388608, 2048, 1]], []], "Input Dims": [[[16, 4096, 2048], [16, 4096, 2048], [16, 4096, 2048], [16, 4096, 2048]], []], "Ev Idx": 8637 + } + }, + { + "ph": "s", "id": 31, "pid": 1336753, "tid": 1336753, "ts": 1712359209617.204, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 1336753, "tid": 1336753, + "ts": 1712359209627.167, "dur": 32.247, + "args": { + "External id": 4722983,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[8388608, 2048, 1], [8388608, 2048, 1], [8388608, 2048, 1], [8388608, 2048, 1]], []], "Input Dims": [[[16, 4096, 2048], [16, 4096, 2048], [16, 4096, 2048], [16, 4096, 2048]], []], "Ev Idx": 8638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359209660.795, "dur": 1.383, + "args": { + "External id": 4722984,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 8192], []], "Ev Idx": 8639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1712359209698.803, "dur": 50.674, + "args": { + "External id": 4722985,"Record function id": 0, "Ev Idx": 8640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 1336753, "tid": 1336753, + "ts": 1712359209751.083, "dur": 196.339, + "args": { + "External id": 4722986,"Record function id": 0, "Ev Idx": 8641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359209789.484, "dur": 149.841, + "args": { + "External id": 4722987,"Sequence number": 47018962, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1], [33554432, 8192, 2048, 1]], "Input Dims": [[2048], [16, 4096, 4, 2048]], "Ev Idx": 8642 + } + }, + { + "ph": "s", "id": 30, "pid": 1336753, "tid": 1336753, "ts": 1712359209789.484, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1712359209862.828, "dur": 38.030, + "args": { + "External id": 4722988,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[262144, 2048], [262144, 2048], [2048], [262144], [], [], [], [], [], [], [], [], []], "Ev Idx": 8643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1712359210092.742, "dur": 43.707, + "args": { + "External id": 4722989,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359210095.567, "dur": 7.168, + "args": { + "External id": 4722990,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210105.535, "dur": 30.604, + "args": { + "External id": 4722991,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 8646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210108.705, "dur": 26.858, + "args": { + "External id": 4722992,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1712359210140.835, "dur": 20.186, + "args": { + "External id": 4722993,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359210142.124, "dur": 2.819, + "args": { + "External id": 4722994,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210147.978, "dur": 12.779, + "args": { + "External id": 4722995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 8650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210148.846, "dur": 11.504, + "args": { + "External id": 4722996,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1712359210163.741, "dur": 16.417, + "args": { + "External id": 4722997,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359210164.517, "dur": 2.563, + "args": { + "External id": 4722998,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210167.737, "dur": 12.172, + "args": { + "External id": 4722999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 8654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210168.515, "dur": 10.947, + "args": { + "External id": 4723000,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359210190.220, "dur": 0.775, + "args": { + "External id": 4723001,"Sequence number": 47018963, "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": [[16, 8192], [], [], [], [], [], [], []], "Ev Idx": 8656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 1336753, "tid": 1336753, + "ts": 1712359210199.519, "dur": 11.375, + "args": { + "External id": 4723002,"Sequence number": 47018963, "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": [[16, 8192], [], [], []], "Ev Idx": 8657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210207.020, "dur": 2.275, + "args": { + "External id": 4723003,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 5]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 8658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210217.026, "dur": 7.542, + "args": { + "External id": 4723004,"Sequence number": 47018963, "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": [[16, 8188, 5], [], [], [], []], "Ev Idx": 8659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210221.728, "dur": 1.050, + "args": { + "External id": 4723005,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 5], [], [], []], "Ev Idx": 8660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210225.862, "dur": 3.446, + "args": { + "External id": 4723006,"Sequence number": 47018963, "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": [[16, 8188, 5], [], [], [], []], "Ev Idx": 8661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210227.906, "dur": 0.651, + "args": { + "External id": 4723007,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 5], [], [], []], "Ev Idx": 8662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210230.795, "dur": 3.173, + "args": { + "External id": 4723008,"Sequence number": 47018963, "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": [[16, 8188, 5], [], [], [], []], "Ev Idx": 8663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210232.546, "dur": 0.894, + "args": { + "External id": 4723009,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 5], [], [], []], "Ev Idx": 8664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210236.824, "dur": 3.781, + "args": { + "External id": 4723010,"Sequence number": 47018963, "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": [[16, 8188, 4], [], [], [], []], "Ev Idx": 8665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210239.213, "dur": 0.860, + "args": { + "External id": 4723011,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 4], [], [], []], "Ev Idx": 8666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210241.521, "dur": 3.509, + "args": { + "External id": 4723012,"Sequence number": 47018963, "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": [[16, 8188, 4], [], [], [], []], "Ev Idx": 8667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210243.757, "dur": 0.423, + "args": { + "External id": 4723013,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 4], [], [], []], "Ev Idx": 8668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210246.490, "dur": 3.329, + "args": { + "External id": 4723014,"Sequence number": 47018963, "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": [[16, 4096, 4], [], [], [], []], "Ev Idx": 8669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210248.582, "dur": 0.758, + "args": { + "External id": 4723015,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4096, 4], [], [], []], "Ev Idx": 8670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359210253.632, "dur": 5.387, + "args": { + "External id": 4723016,"Sequence number": 47018963, "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": [[16, 4096, 4], [], []], "Ev Idx": 8671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210257.414, "dur": 0.807, + "args": { + "External id": 4723017,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4096, 4], [], [], []], "Ev Idx": 8672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210263.165, "dur": 3.313, + "args": { + "External id": 4723018,"Sequence number": 47018963, "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": [[16, 4, 4096], [], [], [], []], "Ev Idx": 8673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210265.098, "dur": 0.810, + "args": { + "External id": 4723019,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 8674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1712359210272.101, "dur": 7.096, + "args": { + "External id": 4723020,"Sequence number": 47018963, "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": [[16, 4, 4096], [], []], "Ev Idx": 8675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210277.285, "dur": 0.851, + "args": { + "External id": 4723021,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 8676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210280.270, "dur": 2.634, + "args": { + "External id": 4723022,"Sequence number": 47018963, "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": [[16, 4096], [], [], [], []], "Ev Idx": 8677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210281.510, "dur": 0.867, + "args": { + "External id": 4723023,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 8678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210285.514, "dur": 8.288, + "args": { + "External id": 4723024,"Sequence number": 47018963, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 8679 + } + }, + { + "ph": "s", "id": 29, "pid": 1336753, "tid": 1336753, "ts": 1712359210285.514, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210291.504, "dur": 0.680, + "args": { + "External id": 4723025,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 8680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210294.862, "dur": 5.483, + "args": { + "External id": 4723026,"Sequence number": 47018964, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 8681 + } + }, + { + "ph": "s", "id": 28, "pid": 1336753, "tid": 1336753, "ts": 1712359210294.862, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210298.597, "dur": 0.997, + "args": { + "External id": 4723027,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 8682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1712359210301.471, "dur": 6.961, + "args": { + "External id": 4723028,"Sequence number": 47018965, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 8683 + } + }, + { + "ph": "s", "id": 27, "pid": 1336753, "tid": 1336753, "ts": 1712359210301.471, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210306.845, "dur": 0.696, + "args": { + "External id": 4723029,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 8684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359210309.496, "dur": 6.658, + "args": { + "External id": 4723030,"Sequence number": 47018966, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 8685 + } + }, + { + "ph": "s", "id": 26, "pid": 1336753, "tid": 1336753, "ts": 1712359210309.496, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210312.366, "dur": 2.793, + "args": { + "External id": 4723031,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 8686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1712359210320.681, "dur": 38.391, + "args": { + "External id": 4723032,"Sequence number": 47018967, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 8687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712359210322.716, "dur": 36.151, + "args": { + "External id": 4723033,"Sequence number": 47018967, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 8688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359210325.477, "dur": 6.404, + "args": { + "External id": 4723034,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 8689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359210327.565, "dur": 3.709, + "args": { + "External id": 4723035,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210333.189, "dur": 25.165, + "args": { + "External id": 4723036,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 8691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359210383.691, "dur": 4.590, + "args": { + "External id": 4723037,"Sequence number": 47018967, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8692 + } + }, + { + "ph": "s", "id": 25, "pid": 1336753, "tid": 1336753, "ts": 1712359210383.691, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359210390.453, "dur": 1.552, + "args": { + "External id": 4723038,"Sequence number": 47018968, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 8693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359210420.567, "dur": 72221.413, + "args": { + "External id": 4723039,"Sequence number": 47018968, "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": [[8192, 1], [1], [2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536], [32000, 2048], [], [], [], [], []], "Ev Idx": 8694 + } + }, + { + "ph": "s", "id": 24, "pid": 1336753, "tid": 1336753, "ts": 1712359210420.567, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1712359210434.453, "dur": 28.302, + "args": { + "External id": 4723040,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712359210435.156, "dur": 27.345, + "args": { + "External id": 4723041,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359210436.863, "dur": 6.795, + "args": { + "External id": 4723042,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359210438.080, "dur": 5.251, + "args": { + "External id": 4723043,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210444.412, "dur": 17.441, + "args": { + "External id": 4723044,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [8192, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 8699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359210479.533, "dur": 23.987, + "args": { + "External id": 4723045,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359210480.464, "dur": 6.460, + "args": { + "External id": 4723046,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210482.772, "dur": 3.835, + "args": { + "External id": 4723047,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210487.953, "dur": 15.351, + "args": { + "External id": 4723048,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 8703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210489.047, "dur": 13.964, + "args": { + "External id": 4723049,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359210506.593, "dur": 32.238, + "args": { + "External id": 4723050,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 8705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359210507.824, "dur": 6.302, + "args": { + "External id": 4723051,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 8706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210511.373, "dur": 2.519, + "args": { + "External id": 4723052,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210526.641, "dur": 11.997, + "args": { + "External id": 4723053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210527.213, "dur": 10.932, + "args": { + "External id": 4723054,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 8709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1712359210542.789, "dur": 18.944, + "args": { + "External id": 4723055,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359210543.968, "dur": 4.970, + "args": { + "External id": 4723056,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210549.751, "dur": 11.751, + "args": { + "External id": 4723057,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 8712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210550.360, "dur": 10.859, + "args": { + "External id": 4723058,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1712359210570.068, "dur": 30.028, + "args": { + "External id": 4723059,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359210603.783, "dur": 60.294, + "args": { + "External id": 4723060,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359210607.141, "dur": 56.420, + "args": { + "External id": 4723061,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210612.719, "dur": 1.305, + "args": { + "External id": 4723062,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359210615.819, "dur": 26.061, + "args": { + "External id": 4723063,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359210617.597, "dur": 24.009, + "args": { + "External id": 4723064,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 8719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359210622.542, "dur": 3.281, + "args": { + "External id": 4723065,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359210626.734, "dur": 14.526, + "args": { + "External id": 4723066,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 8721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1712359210668.790, "dur": 65962.005, + "args": { + "External id": 4723067,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 8722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1712359210671.359, "dur": 65957.174, + "args": { + "External id": 4723068,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 8723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359276646.251, "dur": 10.345, + "args": { + "External id": 4723069,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359276653.203, "dur": 1.317, + "args": { + "External id": 4723070,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359276661.694, "dur": 111.020, + "args": { + "External id": 4723071,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359276663.554, "dur": 9.976, + "args": { + "External id": 4723072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359276666.113, "dur": 6.665, + "args": { + "External id": 4723073,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359276671.833, "dur": 0.700, + "args": { + "External id": 4723074,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359276674.718, "dur": 97.333, + "args": { + "External id": 4723075,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359276678.531, "dur": 92.728, + "args": { + "External id": 4723076,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359276775.653, "dur": 3.806, + "args": { + "External id": 4723077,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359276777.506, "dur": 0.730, + "args": { + "External id": 4723078,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359276787.613, "dur": 3.396, + "args": { + "External id": 4723079,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359276801.369, "dur": 6.810, + "args": { + "External id": 4723080,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359276803.583, "dur": 4.303, + "args": { + "External id": 4723081,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359276951.363, "dur": 300.378, + "args": { + "External id": 4723082,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359276956.668, "dur": 2.146, + "args": { + "External id": 4723083,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359276961.275, "dur": 289.858, + "args": { + "External id": 4723084,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359276964.960, "dur": 0.466, + "args": { + "External id": 4723085,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359276967.437, "dur": 58.278, + "args": { + "External id": 4723086,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359277029.381, "dur": 6.365, + "args": { + "External id": 4723087,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277034.136, "dur": 1.203, + "args": { + "External id": 4723088,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359277038.236, "dur": 45.273, + "args": { + "External id": 4723089,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359277039.837, "dur": 2.301, + "args": { + "External id": 4723090,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359277046.936, "dur": 35.837, + "args": { + "External id": 4723091,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277051.743, "dur": 3.466, + "args": { + "External id": 4723092,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359277086.215, "dur": 30.556, + "args": { + "External id": 4723093,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277119.895, "dur": 18.292, + "args": { + "External id": 4723094,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359277142.241, "dur": 18.300, + "args": { + "External id": 4723095,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277162.711, "dur": 17.395, + "args": { + "External id": 4723096,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359277182.801, "dur": 33.735, + "args": { + "External id": 4723097,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277185.304, "dur": 2.387, + "args": { + "External id": 4723098,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277192.175, "dur": 1.071, + "args": { + "External id": 4723099,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277218.872, "dur": 15.961, + "args": { + "External id": 4723100,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277237.192, "dur": 12.636, + "args": { + "External id": 4723101,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359277260.069, "dur": 2.170, + "args": { + "External id": 4723102,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359277269.457, "dur": 4.579, + "args": { + "External id": 4723103,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277272.286, "dur": 0.888, + "args": { + "External id": 4723104,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359277362.270, "dur": 77.163, + "args": { + "External id": 4723105,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359277444.679, "dur": 7.050, + "args": { + "External id": 4723106,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277449.518, "dur": 0.978, + "args": { + "External id": 4723107,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277453.372, "dur": 36.277, + "args": { + "External id": 4723108,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359277495.089, "dur": 6.166, + "args": { + "External id": 4723109,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359277496.724, "dur": 3.797, + "args": { + "External id": 4723110,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277498.735, "dur": 1.570, + "args": { + "External id": 4723111,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359277505.596, "dur": 50.208, + "args": { + "External id": 4723112,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359277509.107, "dur": 46.014, + "args": { + "External id": 4723113,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277560.232, "dur": 17.475, + "args": { + "External id": 4723114,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359277583.746, "dur": 3.815, + "args": { + "External id": 4723115,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277585.881, "dur": 0.745, + "args": { + "External id": 4723116,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359277591.213, "dur": 51.210, + "args": { + "External id": 4723117,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359277592.557, "dur": 6.391, + "args": { + "External id": 4723118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359277593.542, "dur": 4.882, + "args": { + "External id": 4723119,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277597.290, "dur": 1.001, + "args": { + "External id": 4723120,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359277599.662, "dur": 42.419, + "args": { + "External id": 4723121,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359277600.271, "dur": 41.327, + "args": { + "External id": 4723122,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359277645.906, "dur": 5.915, + "args": { + "External id": 4723123,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277647.920, "dur": 2.871, + "args": { + "External id": 4723124,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359277657.655, "dur": 1.380, + "args": { + "External id": 4723125,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359277669.499, "dur": 5.860, + "args": { + "External id": 4723126,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359277671.412, "dur": 3.686, + "args": { + "External id": 4723127,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359277769.765, "dur": 193.465, + "args": { + "External id": 4723128,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359277771.804, "dur": 2.733, + "args": { + "External id": 4723129,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359277776.193, "dur": 186.556, + "args": { + "External id": 4723130,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359277778.102, "dur": 0.585, + "args": { + "External id": 4723131,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359277782.329, "dur": 24.430, + "args": { + "External id": 4723132,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359277808.264, "dur": 3.284, + "args": { + "External id": 4723133,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277810.523, "dur": 0.798, + "args": { + "External id": 4723134,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359277812.484, "dur": 25.643, + "args": { + "External id": 4723135,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359277813.986, "dur": 1.948, + "args": { + "External id": 4723136,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359277817.247, "dur": 20.532, + "args": { + "External id": 4723137,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277821.938, "dur": 2.744, + "args": { + "External id": 4723138,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359277839.899, "dur": 20.657, + "args": { + "External id": 4723139,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277862.117, "dur": 14.496, + "args": { + "External id": 4723140,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359277880.018, "dur": 14.881, + "args": { + "External id": 4723141,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277898.468, "dur": 12.989, + "args": { + "External id": 4723142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359277913.142, "dur": 21.440, + "args": { + "External id": 4723143,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277914.903, "dur": 1.658, + "args": { + "External id": 4723144,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359277918.594, "dur": 0.952, + "args": { + "External id": 4723145,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277936.037, "dur": 13.124, + "args": { + "External id": 4723146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359277950.013, "dur": 11.349, + "args": { + "External id": 4723147,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359277971.337, "dur": 1.711, + "args": { + "External id": 4723148,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359278018.821, "dur": 5.028, + "args": { + "External id": 4723149,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278021.541, "dur": 0.915, + "args": { + "External id": 4723150,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359278116.590, "dur": 59.003, + "args": { + "External id": 4723151,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359278180.995, "dur": 5.659, + "args": { + "External id": 4723152,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278183.833, "dur": 1.281, + "args": { + "External id": 4723153,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359278188.190, "dur": 28.007, + "args": { + "External id": 4723154,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359278221.157, "dur": 8.342, + "args": { + "External id": 4723155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359278222.828, "dur": 5.985, + "args": { + "External id": 4723156,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278227.301, "dur": 1.328, + "args": { + "External id": 4723157,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359278232.717, "dur": 42.980, + "args": { + "External id": 4723158,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359278233.767, "dur": 41.453, + "args": { + "External id": 4723159,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359278279.667, "dur": 20.417, + "args": { + "External id": 4723160,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359278305.929, "dur": 3.710, + "args": { + "External id": 4723161,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278308.026, "dur": 0.804, + "args": { + "External id": 4723162,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359278315.699, "dur": 50.241, + "args": { + "External id": 4723163,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359278316.705, "dur": 6.574, + "args": { + "External id": 4723164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359278317.642, "dur": 4.846, + "args": { + "External id": 4723165,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278321.664, "dur": 0.678, + "args": { + "External id": 4723166,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359278324.003, "dur": 41.577, + "args": { + "External id": 4723167,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359278324.723, "dur": 40.164, + "args": { + "External id": 4723168,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359278369.787, "dur": 3.866, + "args": { + "External id": 4723169,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278371.960, "dur": 0.755, + "args": { + "External id": 4723170,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359278382.312, "dur": 1.529, + "args": { + "External id": 4723171,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359278391.986, "dur": 6.174, + "args": { + "External id": 4723172,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359278394.120, "dur": 3.744, + "args": { + "External id": 4723173,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359278482.190, "dur": 322.587, + "args": { + "External id": 4723174,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359278484.301, "dur": 2.569, + "args": { + "External id": 4723175,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359278488.400, "dur": 315.848, + "args": { + "External id": 4723176,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359278492.175, "dur": 0.320, + "args": { + "External id": 4723177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359278495.724, "dur": 23.243, + "args": { + "External id": 4723178,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359278520.879, "dur": 3.225, + "args": { + "External id": 4723179,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278522.864, "dur": 1.002, + "args": { + "External id": 4723180,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359278525.026, "dur": 26.277, + "args": { + "External id": 4723181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359278528.600, "dur": 1.452, + "args": { + "External id": 4723182,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359278531.355, "dur": 19.613, + "args": { + "External id": 4723183,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359278533.858, "dur": 2.768, + "args": { + "External id": 4723184,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359278553.138, "dur": 23.349, + "args": { + "External id": 4723185,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359278578.081, "dur": 41.553, + "args": { + "External id": 4723186,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359278622.527, "dur": 39.408, + "args": { + "External id": 4723187,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359278665.614, "dur": 36.389, + "args": { + "External id": 4723188,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359278703.701, "dur": 39.352, + "args": { + "External id": 4723189,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359278705.383, "dur": 1.711, + "args": { + "External id": 4723190,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278709.023, "dur": 0.602, + "args": { + "External id": 4723191,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359278744.639, "dur": 28.390, + "args": { + "External id": 4723192,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359278774.140, "dur": 29.022, + "args": { + "External id": 4723193,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359278813.052, "dur": 1.745, + "args": { + "External id": 4723194,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359278822.763, "dur": 2.955, + "args": { + "External id": 4723195,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278824.637, "dur": 0.331, + "args": { + "External id": 4723196,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359278887.681, "dur": 47.012, + "args": { + "External id": 4723197,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359278938.912, "dur": 6.643, + "args": { + "External id": 4723198,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359278941.267, "dur": 3.261, + "args": { + "External id": 4723199,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359278946.689, "dur": 25.945, + "args": { + "External id": 4723200,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359279116.309, "dur": 10.765, + "args": { + "External id": 4723201,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359279121.820, "dur": 4.142, + "args": { + "External id": 4723202,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279124.423, "dur": 1.104, + "args": { + "External id": 4723203,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359279131.576, "dur": 54.500, + "args": { + "External id": 4723204,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359279132.599, "dur": 52.805, + "args": { + "External id": 4723205,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359279190.715, "dur": 17.746, + "args": { + "External id": 4723206,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359279215.045, "dur": 7.141, + "args": { + "External id": 4723207,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279219.835, "dur": 1.246, + "args": { + "External id": 4723208,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359279226.118, "dur": 48.049, + "args": { + "External id": 4723209,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359279226.939, "dur": 3.373, + "args": { + "External id": 4723210,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359279227.773, "dur": 2.051, + "args": { + "External id": 4723211,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279228.913, "dur": 0.766, + "args": { + "External id": 4723212,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359279230.830, "dur": 42.912, + "args": { + "External id": 4723213,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359279231.342, "dur": 41.772, + "args": { + "External id": 4723214,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359279279.962, "dur": 3.902, + "args": { + "External id": 4723215,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279282.108, "dur": 0.586, + "args": { + "External id": 4723216,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359279290.585, "dur": 1.428, + "args": { + "External id": 4723217,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359279300.551, "dur": 9.209, + "args": { + "External id": 4723218,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359279302.222, "dur": 7.248, + "args": { + "External id": 4723219,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359279403.998, "dur": 201.927, + "args": { + "External id": 4723220,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359279405.762, "dur": 2.496, + "args": { + "External id": 4723221,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359279409.883, "dur": 195.588, + "args": { + "External id": 4723222,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359279411.363, "dur": 0.331, + "args": { + "External id": 4723223,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359279412.715, "dur": 25.633, + "args": { + "External id": 4723224,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359279439.998, "dur": 3.704, + "args": { + "External id": 4723225,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279442.414, "dur": 1.041, + "args": { + "External id": 4723226,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359279444.589, "dur": 29.390, + "args": { + "External id": 4723227,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359279445.870, "dur": 1.514, + "args": { + "External id": 4723228,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359279450.988, "dur": 22.585, + "args": { + "External id": 4723229,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359279456.706, "dur": 2.859, + "args": { + "External id": 4723230,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359279475.439, "dur": 21.885, + "args": { + "External id": 4723231,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359279498.764, "dur": 15.098, + "args": { + "External id": 4723232,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359279517.079, "dur": 14.197, + "args": { + "External id": 4723233,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359279532.702, "dur": 18.887, + "args": { + "External id": 4723234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359279553.432, "dur": 23.272, + "args": { + "External id": 4723235,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359279555.050, "dur": 1.592, + "args": { + "External id": 4723236,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279561.674, "dur": 1.003, + "args": { + "External id": 4723237,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359279578.253, "dur": 13.567, + "args": { + "External id": 4723238,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359279592.852, "dur": 11.431, + "args": { + "External id": 4723239,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359279611.864, "dur": 1.563, + "args": { + "External id": 4723240,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359279621.715, "dur": 3.227, + "args": { + "External id": 4723241,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279623.805, "dur": 0.337, + "args": { + "External id": 4723242,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359279686.818, "dur": 46.789, + "args": { + "External id": 4723243,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359279738.227, "dur": 6.671, + "args": { + "External id": 4723244,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279742.635, "dur": 1.368, + "args": { + "External id": 4723245,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359279746.350, "dur": 25.776, + "args": { + "External id": 4723246,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359279776.267, "dur": 4.713, + "args": { + "External id": 4723247,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359279777.434, "dur": 2.987, + "args": { + "External id": 4723248,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279779.107, "dur": 1.153, + "args": { + "External id": 4723249,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359279783.257, "dur": 38.365, + "args": { + "External id": 4723250,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359279784.210, "dur": 36.854, + "args": { + "External id": 4723251,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359279827.289, "dur": 13.626, + "args": { + "External id": 4723252,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359279845.267, "dur": 3.480, + "args": { + "External id": 4723253,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279847.207, "dur": 0.748, + "args": { + "External id": 4723254,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359279851.664, "dur": 48.870, + "args": { + "External id": 4723255,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359279852.659, "dur": 6.591, + "args": { + "External id": 4723256,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359279853.407, "dur": 5.357, + "args": { + "External id": 4723257,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279857.280, "dur": 1.242, + "args": { + "External id": 4723258,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359279859.903, "dur": 40.272, + "args": { + "External id": 4723259,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359279860.523, "dur": 39.139, + "args": { + "External id": 4723260,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359279903.991, "dur": 5.666, + "args": { + "External id": 4723261,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359279905.783, "dur": 2.773, + "args": { + "External id": 4723262,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359279914.665, "dur": 1.119, + "args": { + "External id": 4723263,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359279922.377, "dur": 7.812, + "args": { + "External id": 4723264,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359279926.310, "dur": 3.630, + "args": { + "External id": 4723265,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359280043.865, "dur": 221.857, + "args": { + "External id": 4723266,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359280046.260, "dur": 3.328, + "args": { + "External id": 4723267,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359280051.119, "dur": 214.163, + "args": { + "External id": 4723268,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359280052.331, "dur": 0.275, + "args": { + "External id": 4723269,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359280054.192, "dur": 39.823, + "args": { + "External id": 4723270,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359280096.435, "dur": 4.294, + "args": { + "External id": 4723271,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280098.896, "dur": 1.512, + "args": { + "External id": 4723272,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359280102.044, "dur": 27.998, + "args": { + "External id": 4723273,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359280102.944, "dur": 1.993, + "args": { + "External id": 4723274,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359280108.221, "dur": 21.451, + "args": { + "External id": 4723275,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280113.837, "dur": 3.023, + "args": { + "External id": 4723276,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359280131.543, "dur": 23.004, + "args": { + "External id": 4723277,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280155.816, "dur": 13.939, + "args": { + "External id": 4723278,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359280173.020, "dur": 15.623, + "args": { + "External id": 4723279,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280189.810, "dur": 18.759, + "args": { + "External id": 4723280,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359280210.561, "dur": 26.893, + "args": { + "External id": 4723281,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280212.289, "dur": 2.046, + "args": { + "External id": 4723282,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280219.002, "dur": 1.372, + "args": { + "External id": 4723283,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280238.944, "dur": 13.001, + "args": { + "External id": 4723284,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280252.941, "dur": 11.412, + "args": { + "External id": 4723285,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359280273.103, "dur": 2.156, + "args": { + "External id": 4723286,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359280284.585, "dur": 3.821, + "args": { + "External id": 4723287,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280286.928, "dur": 0.580, + "args": { + "External id": 4723288,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359280352.188, "dur": 54.278, + "args": { + "External id": 4723289,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359280411.092, "dur": 6.928, + "args": { + "External id": 4723290,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280415.473, "dur": 1.629, + "args": { + "External id": 4723291,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280419.613, "dur": 24.777, + "args": { + "External id": 4723292,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359280448.429, "dur": 5.935, + "args": { + "External id": 4723293,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359280450.098, "dur": 3.418, + "args": { + "External id": 4723294,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280452.346, "dur": 0.996, + "args": { + "External id": 4723295,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359280456.987, "dur": 41.158, + "args": { + "External id": 4723296,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359280460.314, "dur": 37.261, + "args": { + "External id": 4723297,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280501.748, "dur": 16.139, + "args": { + "External id": 4723298,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359280522.837, "dur": 3.686, + "args": { + "External id": 4723299,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280524.751, "dur": 1.014, + "args": { + "External id": 4723300,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359280530.267, "dur": 50.476, + "args": { + "External id": 4723301,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359280531.341, "dur": 7.858, + "args": { + "External id": 4723302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359280532.128, "dur": 6.539, + "args": { + "External id": 4723303,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280537.858, "dur": 0.687, + "args": { + "External id": 4723304,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359280539.763, "dur": 40.631, + "args": { + "External id": 4723305,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359280540.368, "dur": 39.602, + "args": { + "External id": 4723306,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359280584.071, "dur": 3.586, + "args": { + "External id": 4723307,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280585.924, "dur": 0.658, + "args": { + "External id": 4723308,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359280614.911, "dur": 1.818, + "args": { + "External id": 4723309,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359280627.379, "dur": 6.828, + "args": { + "External id": 4723310,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359280629.486, "dur": 4.473, + "args": { + "External id": 4723311,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359280716.475, "dur": 221.100, + "args": { + "External id": 4723312,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359280720.941, "dur": 2.615, + "args": { + "External id": 4723313,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359280724.623, "dur": 212.541, + "args": { + "External id": 4723314,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359280752.835, "dur": 0.441, + "args": { + "External id": 4723315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359280760.042, "dur": 22.858, + "args": { + "External id": 4723316,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359280784.300, "dur": 5.903, + "args": { + "External id": 4723317,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280789.100, "dur": 0.867, + "args": { + "External id": 4723318,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359280791.026, "dur": 22.418, + "args": { + "External id": 4723319,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359280792.296, "dur": 1.738, + "args": { + "External id": 4723320,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359280795.210, "dur": 17.950, + "args": { + "External id": 4723321,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280798.135, "dur": 2.494, + "args": { + "External id": 4723322,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359280814.712, "dur": 20.475, + "args": { + "External id": 4723323,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280836.478, "dur": 16.719, + "args": { + "External id": 4723324,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359280856.053, "dur": 13.810, + "args": { + "External id": 4723325,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280873.426, "dur": 13.405, + "args": { + "External id": 4723326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359280888.658, "dur": 20.929, + "args": { + "External id": 4723327,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280890.084, "dur": 1.824, + "args": { + "External id": 4723328,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280894.628, "dur": 1.014, + "args": { + "External id": 4723329,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280911.127, "dur": 13.342, + "args": { + "External id": 4723330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359280925.543, "dur": 10.522, + "args": { + "External id": 4723331,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359280945.812, "dur": 1.627, + "args": { + "External id": 4723332,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359280955.760, "dur": 3.691, + "args": { + "External id": 4723333,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359280958.079, "dur": 0.583, + "args": { + "External id": 4723334,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359281095.592, "dur": 61.670, + "args": { + "External id": 4723335,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359281162.755, "dur": 5.943, + "args": { + "External id": 4723336,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281166.081, "dur": 1.070, + "args": { + "External id": 4723337,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281170.131, "dur": 26.062, + "args": { + "External id": 4723338,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359281201.120, "dur": 9.151, + "args": { + "External id": 4723339,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359281202.805, "dur": 6.799, + "args": { + "External id": 4723340,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281207.653, "dur": 1.751, + "args": { + "External id": 4723341,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359281212.805, "dur": 40.515, + "args": { + "External id": 4723342,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359281213.959, "dur": 38.815, + "args": { + "External id": 4723343,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281257.320, "dur": 16.101, + "args": { + "External id": 4723344,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359281278.357, "dur": 3.539, + "args": { + "External id": 4723345,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281280.209, "dur": 0.965, + "args": { + "External id": 4723346,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359281287.934, "dur": 46.043, + "args": { + "External id": 4723347,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359281288.761, "dur": 3.729, + "args": { + "External id": 4723348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359281289.709, "dur": 2.311, + "args": { + "External id": 4723349,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281291.128, "dur": 0.781, + "args": { + "External id": 4723350,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359281293.167, "dur": 40.438, + "args": { + "External id": 4723351,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359281293.902, "dur": 39.140, + "args": { + "External id": 4723352,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359281337.506, "dur": 3.727, + "args": { + "External id": 4723353,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281339.228, "dur": 0.906, + "args": { + "External id": 4723354,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359281350.258, "dur": 1.557, + "args": { + "External id": 4723355,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359281358.862, "dur": 8.615, + "args": { + "External id": 4723356,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359281360.843, "dur": 6.336, + "args": { + "External id": 4723357,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359281450.589, "dur": 192.491, + "args": { + "External id": 4723358,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359281452.756, "dur": 2.098, + "args": { + "External id": 4723359,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359281456.012, "dur": 186.602, + "args": { + "External id": 4723360,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359281459.957, "dur": 0.458, + "args": { + "External id": 4723361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359281461.586, "dur": 23.651, + "args": { + "External id": 4723362,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359281486.703, "dur": 3.997, + "args": { + "External id": 4723363,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281489.222, "dur": 1.208, + "args": { + "External id": 4723364,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359281491.730, "dur": 24.802, + "args": { + "External id": 4723365,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359281492.833, "dur": 1.665, + "args": { + "External id": 4723366,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359281495.741, "dur": 20.492, + "args": { + "External id": 4723367,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281500.804, "dur": 2.663, + "args": { + "External id": 4723368,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359281517.980, "dur": 21.301, + "args": { + "External id": 4723369,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281540.471, "dur": 13.756, + "args": { + "External id": 4723370,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359281557.182, "dur": 14.383, + "args": { + "External id": 4723371,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281575.738, "dur": 12.629, + "args": { + "External id": 4723372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359281590.142, "dur": 21.336, + "args": { + "External id": 4723373,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281591.830, "dur": 1.877, + "args": { + "External id": 4723374,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281596.020, "dur": 0.813, + "args": { + "External id": 4723375,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281612.798, "dur": 12.951, + "args": { + "External id": 4723376,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281626.712, "dur": 12.614, + "args": { + "External id": 4723377,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359281648.564, "dur": 1.540, + "args": { + "External id": 4723378,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359281657.860, "dur": 3.544, + "args": { + "External id": 4723379,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281660.040, "dur": 0.638, + "args": { + "External id": 4723380,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359281719.956, "dur": 48.465, + "args": { + "External id": 4723381,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359281772.438, "dur": 4.461, + "args": { + "External id": 4723382,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281774.471, "dur": 1.507, + "args": { + "External id": 4723383,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281777.931, "dur": 23.840, + "args": { + "External id": 4723384,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359281805.762, "dur": 7.941, + "args": { + "External id": 4723385,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359281809.293, "dur": 3.816, + "args": { + "External id": 4723386,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281811.307, "dur": 1.637, + "args": { + "External id": 4723387,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359281815.874, "dur": 38.229, + "args": { + "External id": 4723388,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359281816.794, "dur": 36.695, + "args": { + "External id": 4723389,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359281857.201, "dur": 14.772, + "args": { + "External id": 4723390,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359281876.453, "dur": 5.493, + "args": { + "External id": 4723391,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281880.407, "dur": 0.829, + "args": { + "External id": 4723392,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359281884.989, "dur": 47.864, + "args": { + "External id": 4723393,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359281885.944, "dur": 5.076, + "args": { + "External id": 4723394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359281886.511, "dur": 3.952, + "args": { + "External id": 4723395,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281888.026, "dur": 2.229, + "args": { + "External id": 4723396,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359281891.665, "dur": 40.785, + "args": { + "External id": 4723397,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359281892.372, "dur": 39.585, + "args": { + "External id": 4723398,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359281938.673, "dur": 3.714, + "args": { + "External id": 4723399,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359281940.430, "dur": 0.957, + "args": { + "External id": 4723400,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359281947.381, "dur": 1.104, + "args": { + "External id": 4723401,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359281954.439, "dur": 5.320, + "args": { + "External id": 4723402,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359281955.889, "dur": 3.641, + "args": { + "External id": 4723403,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359282096.376, "dur": 191.844, + "args": { + "External id": 4723404,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359282099.509, "dur": 3.067, + "args": { + "External id": 4723405,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359282103.688, "dur": 184.068, + "args": { + "External id": 4723406,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359282104.803, "dur": 0.419, + "args": { + "External id": 4723407,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359282108.798, "dur": 23.478, + "args": { + "External id": 4723408,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359282133.646, "dur": 3.753, + "args": { + "External id": 4723409,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282136.026, "dur": 1.053, + "args": { + "External id": 4723410,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359282138.378, "dur": 26.803, + "args": { + "External id": 4723411,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359282139.527, "dur": 3.377, + "args": { + "External id": 4723412,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359282146.691, "dur": 18.059, + "args": { + "External id": 4723413,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282149.865, "dur": 2.479, + "args": { + "External id": 4723414,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359282166.343, "dur": 20.987, + "args": { + "External id": 4723415,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282188.449, "dur": 14.349, + "args": { + "External id": 4723416,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359282205.439, "dur": 14.130, + "args": { + "External id": 4723417,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282220.870, "dur": 13.758, + "args": { + "External id": 4723418,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359282236.575, "dur": 23.349, + "args": { + "External id": 4723419,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282238.183, "dur": 1.680, + "args": { + "External id": 4723420,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282244.475, "dur": 1.192, + "args": { + "External id": 4723421,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282261.478, "dur": 12.991, + "args": { + "External id": 4723422,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282275.492, "dur": 10.966, + "args": { + "External id": 4723423,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359282294.572, "dur": 1.903, + "args": { + "External id": 4723424,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359282305.154, "dur": 3.516, + "args": { + "External id": 4723425,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282307.425, "dur": 0.474, + "args": { + "External id": 4723426,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359282371.120, "dur": 52.370, + "args": { + "External id": 4723427,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359282428.143, "dur": 6.669, + "args": { + "External id": 4723428,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282432.687, "dur": 1.178, + "args": { + "External id": 4723429,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282436.149, "dur": 23.193, + "args": { + "External id": 4723430,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359282463.370, "dur": 6.927, + "args": { + "External id": 4723431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359282464.880, "dur": 4.705, + "args": { + "External id": 4723432,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282466.775, "dur": 2.605, + "args": { + "External id": 4723433,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359282472.836, "dur": 39.142, + "args": { + "External id": 4723434,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359282473.834, "dur": 37.382, + "args": { + "External id": 4723435,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282517.493, "dur": 14.447, + "args": { + "External id": 4723436,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359282536.200, "dur": 25.073, + "args": { + "External id": 4723437,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359282538.287, "dur": 22.622, + "args": { + "External id": 4723438,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282543.346, "dur": 1.346, + "args": { + "External id": 4723439,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359282566.820, "dur": 28.149, + "args": { + "External id": 4723440,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359282568.449, "dur": 26.281, + "args": { + "External id": 4723441,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 9096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282572.538, "dur": 4.167, + "args": { + "External id": 4723442,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282577.673, "dur": 16.564, + "args": { + "External id": 4723443,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359282608.874, "dur": 7.851, + "args": { + "External id": 4723444,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359282613.138, "dur": 3.331, + "args": { + "External id": 4723445,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359282617.645, "dur": 1.321, + "args": { + "External id": 4723446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359282618.393, "dur": 0.469, + "args": { + "External id": 4723447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282657.782, "dur": 22.586, + "args": { + "External id": 4723448,"Sequence number": 47018969, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9103 + } + }, + { + "ph": "s", "id": 23, "pid": 1336753, "tid": 1336753, "ts": 1712359282657.782, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359282686.190, "dur": 5.669, + "args": { + "External id": 4723449,"Sequence number": 47018970, "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": [[16, 4, 4096], [], [], [], []], "Ev Idx": 9104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282689.849, "dur": 0.897, + "args": { + "External id": 4723450,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1712359282694.332, "dur": 8.098, + "args": { + "External id": 4723451,"Sequence number": 47018970, "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": [[16, 4, 4096], [], []], "Ev Idx": 9106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282700.473, "dur": 0.812, + "args": { + "External id": 4723452,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359282703.665, "dur": 2.420, + "args": { + "External id": 4723453,"Sequence number": 47018970, "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": [[16, 4096], [], [], [], []], "Ev Idx": 9108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282704.881, "dur": 0.667, + "args": { + "External id": 4723454,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 9109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359282709.977, "dur": 6.092, + "args": { + "External id": 4723455,"Sequence number": 47018970, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9110 + } + }, + { + "ph": "s", "id": 22, "pid": 1336753, "tid": 1336753, "ts": 1712359282709.977, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282713.705, "dur": 1.046, + "args": { + "External id": 4723456,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359282719.606, "dur": 5.386, + "args": { + "External id": 4723457,"Sequence number": 47018971, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9112 + } + }, + { + "ph": "s", "id": 21, "pid": 1336753, "tid": 1336753, "ts": 1712359282719.606, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282723.111, "dur": 1.128, + "args": { + "External id": 4723458,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1712359282726.072, "dur": 5.175, + "args": { + "External id": 4723459,"Sequence number": 47018972, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 9114 + } + }, + { + "ph": "s", "id": 20, "pid": 1336753, "tid": 1336753, "ts": 1712359282726.072, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282729.859, "dur": 0.598, + "args": { + "External id": 4723460,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359282732.379, "dur": 4.913, + "args": { + "External id": 4723461,"Sequence number": 47018973, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 9116 + } + }, + { + "ph": "s", "id": 19, "pid": 1336753, "tid": 1336753, "ts": 1712359282732.379, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282735.275, "dur": 1.349, + "args": { + "External id": 4723462,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 9117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1712359282741.461, "dur": 32.103, + "args": { + "External id": 4723463,"Sequence number": 47018974, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712359282745.154, "dur": 28.213, + "args": { + "External id": 4723464,"Sequence number": 47018974, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359282747.603, "dur": 6.232, + "args": { + "External id": 4723465,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 9120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359282749.893, "dur": 3.371, + "args": { + "External id": 4723466,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282754.623, "dur": 18.239, + "args": { + "External id": 4723467,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 9122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359282797.152, "dur": 3.460, + "args": { + "External id": 4723468,"Sequence number": 47018974, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 9123 + } + }, + { + "ph": "s", "id": 18, "pid": 1336753, "tid": 1336753, "ts": 1712359282797.152, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359282802.895, "dur": 0.918, + "args": { + "External id": 4723469,"Sequence number": 47018975, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359282838.127, "dur": 42623.929, + "args": { + "External id": 4723470,"Sequence number": 47018975, "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": [[8192, 1], [1], [2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536], [32000, 2048], [], [], [], [], []], "Ev Idx": 9125 + } + }, + { + "ph": "s", "id": 17, "pid": 1336753, "tid": 1336753, "ts": 1712359282838.127, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1712359282851.408, "dur": 24.386, + "args": { + "External id": 4723471,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712359282852.061, "dur": 23.545, + "args": { + "External id": 4723472,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359282853.401, "dur": 4.674, + "args": { + "External id": 4723473,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359282854.551, "dur": 3.120, + "args": { + "External id": 4723474,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282858.900, "dur": 16.398, + "args": { + "External id": 4723475,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [8192, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 9130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359282890.768, "dur": 24.280, + "args": { + "External id": 4723476,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359282891.764, "dur": 5.703, + "args": { + "External id": 4723477,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282893.573, "dur": 3.541, + "args": { + "External id": 4723478,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282898.545, "dur": 16.290, + "args": { + "External id": 4723479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282900.089, "dur": 14.319, + "args": { + "External id": 4723480,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359282917.974, "dur": 22.696, + "args": { + "External id": 4723481,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359282919.518, "dur": 7.124, + "args": { + "External id": 4723482,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359282923.189, "dur": 3.212, + "args": { + "External id": 4723483,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282927.338, "dur": 13.139, + "args": { + "External id": 4723484,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282927.825, "dur": 12.337, + "args": { + "External id": 4723485,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 9140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1712359282946.464, "dur": 18.600, + "args": { + "External id": 4723486,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359282947.995, "dur": 3.298, + "args": { + "External id": 4723487,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282951.858, "dur": 12.914, + "args": { + "External id": 4723488,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 9143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359282954.548, "dur": 9.896, + "args": { + "External id": 4723489,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1712359282969.522, "dur": 65.073, + "args": { + "External id": 4723490,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359283041.470, "dur": 104.750, + "args": { + "External id": 4723491,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359283089.006, "dur": 56.716, + "args": { + "External id": 4723492,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359283096.219, "dur": 3.216, + "args": { + "External id": 4723493,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359283101.048, "dur": 26.400, + "args": { + "External id": 4723494,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359283102.483, "dur": 24.711, + "args": { + "External id": 4723495,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 9150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359283105.208, "dur": 3.414, + "args": { + "External id": 4723496,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359283109.478, "dur": 17.299, + "args": { + "External id": 4723497,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 9152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1712359283151.036, "dur": 36597.412, + "args": { + "External id": 4723498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1712359283152.525, "dur": 36595.218, + "args": { + "External id": 4723499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359319758.861, "dur": 7.651, + "args": { + "External id": 4723500,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359319763.356, "dur": 1.375, + "args": { + "External id": 4723501,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359319773.515, "dur": 101.201, + "args": { + "External id": 4723502,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359319775.191, "dur": 6.284, + "args": { + "External id": 4723503,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359319777.535, "dur": 3.029, + "args": { + "External id": 4723504,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359319779.256, "dur": 1.043, + "args": { + "External id": 4723505,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359319782.817, "dur": 91.335, + "args": { + "External id": 4723506,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359319784.288, "dur": 89.111, + "args": { + "External id": 4723507,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359319878.052, "dur": 4.291, + "args": { + "External id": 4723508,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359319880.290, "dur": 0.851, + "args": { + "External id": 4723509,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359319891.576, "dur": 2.336, + "args": { + "External id": 4723510,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359319902.533, "dur": 6.517, + "args": { + "External id": 4723511,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359319904.381, "dur": 4.324, + "args": { + "External id": 4723512,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359320080.703, "dur": 219.210, + "args": { + "External id": 4723513,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359320085.578, "dur": 3.594, + "args": { + "External id": 4723514,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359320093.203, "dur": 206.093, + "args": { + "External id": 4723515,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359320094.949, "dur": 0.615, + "args": { + "External id": 4723516,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359320096.885, "dur": 28.252, + "args": { + "External id": 4723517,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359320126.815, "dur": 6.221, + "args": { + "External id": 4723518,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320131.423, "dur": 1.082, + "args": { + "External id": 4723519,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359320133.964, "dur": 25.215, + "args": { + "External id": 4723520,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359320135.261, "dur": 1.852, + "args": { + "External id": 4723521,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359320138.489, "dur": 20.352, + "args": { + "External id": 4723522,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320142.296, "dur": 3.503, + "args": { + "External id": 4723523,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359320163.234, "dur": 23.720, + "args": { + "External id": 4723524,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320188.885, "dur": 17.666, + "args": { + "External id": 4723525,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359320209.871, "dur": 16.646, + "args": { + "External id": 4723526,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320228.038, "dur": 14.612, + "args": { + "External id": 4723527,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359320244.589, "dur": 21.800, + "args": { + "External id": 4723528,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320246.736, "dur": 1.542, + "args": { + "External id": 4723529,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320250.163, "dur": 0.879, + "args": { + "External id": 4723530,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320270.539, "dur": 13.269, + "args": { + "External id": 4723531,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320285.483, "dur": 12.787, + "args": { + "External id": 4723532,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359320307.428, "dur": 2.203, + "args": { + "External id": 4723533,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359320316.685, "dur": 3.973, + "args": { + "External id": 4723534,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320319.151, "dur": 0.791, + "args": { + "External id": 4723535,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359320397.573, "dur": 69.644, + "args": { + "External id": 4723536,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359320472.232, "dur": 6.888, + "args": { + "External id": 4723537,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320475.465, "dur": 1.361, + "args": { + "External id": 4723538,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320483.024, "dur": 30.291, + "args": { + "External id": 4723539,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359320518.497, "dur": 5.988, + "args": { + "External id": 4723540,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359320520.219, "dur": 3.567, + "args": { + "External id": 4723541,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320522.189, "dur": 1.385, + "args": { + "External id": 4723542,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359320527.301, "dur": 43.712, + "args": { + "External id": 4723543,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359320528.300, "dur": 42.094, + "args": { + "External id": 4723544,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320574.978, "dur": 16.645, + "args": { + "External id": 4723545,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359320599.219, "dur": 3.733, + "args": { + "External id": 4723546,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320601.510, "dur": 0.722, + "args": { + "External id": 4723547,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359320607.021, "dur": 57.138, + "args": { + "External id": 4723548,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359320607.957, "dur": 3.633, + "args": { + "External id": 4723549,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359320608.688, "dur": 2.441, + "args": { + "External id": 4723550,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320610.112, "dur": 0.844, + "args": { + "External id": 4723551,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359320614.602, "dur": 49.016, + "args": { + "External id": 4723552,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359320620.195, "dur": 42.904, + "args": { + "External id": 4723553,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359320667.601, "dur": 3.791, + "args": { + "External id": 4723554,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320669.429, "dur": 0.886, + "args": { + "External id": 4723555,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359320676.945, "dur": 1.578, + "args": { + "External id": 4723556,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359320686.235, "dur": 10.732, + "args": { + "External id": 4723557,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359320690.924, "dur": 5.723, + "args": { + "External id": 4723558,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359320785.293, "dur": 190.705, + "args": { + "External id": 4723559,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359320787.069, "dur": 2.115, + "args": { + "External id": 4723560,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359320790.876, "dur": 184.649, + "args": { + "External id": 4723561,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359320792.502, "dur": 0.417, + "args": { + "External id": 4723562,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359320794.016, "dur": 24.781, + "args": { + "External id": 4723563,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359320823.234, "dur": 2.937, + "args": { + "External id": 4723564,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320825.248, "dur": 0.692, + "args": { + "External id": 4723565,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359320829.835, "dur": 25.293, + "args": { + "External id": 4723566,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359320831.012, "dur": 3.407, + "args": { + "External id": 4723567,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359320835.753, "dur": 19.128, + "args": { + "External id": 4723568,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320837.966, "dur": 3.077, + "args": { + "External id": 4723569,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359320856.508, "dur": 19.517, + "args": { + "External id": 4723570,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320877.465, "dur": 14.414, + "args": { + "External id": 4723571,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359320894.505, "dur": 13.811, + "args": { + "External id": 4723572,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320909.557, "dur": 13.226, + "args": { + "External id": 4723573,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359320924.259, "dur": 23.310, + "args": { + "External id": 4723574,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320928.252, "dur": 1.516, + "args": { + "External id": 4723575,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359320932.021, "dur": 0.595, + "args": { + "External id": 4723576,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320949.047, "dur": 13.161, + "args": { + "External id": 4723577,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359320963.169, "dur": 11.104, + "args": { + "External id": 4723578,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359321018.858, "dur": 2.216, + "args": { + "External id": 4723579,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359321031.815, "dur": 3.400, + "args": { + "External id": 4723580,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321033.829, "dur": 0.558, + "args": { + "External id": 4723581,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359321124.035, "dur": 57.614, + "args": { + "External id": 4723582,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359321188.946, "dur": 5.682, + "args": { + "External id": 4723583,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321191.909, "dur": 1.290, + "args": { + "External id": 4723584,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321195.962, "dur": 25.006, + "args": { + "External id": 4723585,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359321225.955, "dur": 6.966, + "args": { + "External id": 4723586,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359321227.388, "dur": 4.854, + "args": { + "External id": 4723587,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321229.162, "dur": 2.868, + "args": { + "External id": 4723588,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359321237.848, "dur": 39.955, + "args": { + "External id": 4723589,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359321238.854, "dur": 38.371, + "args": { + "External id": 4723590,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321281.550, "dur": 16.144, + "args": { + "External id": 4723591,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359321303.157, "dur": 3.667, + "args": { + "External id": 4723592,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321305.203, "dur": 0.854, + "args": { + "External id": 4723593,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359321310.563, "dur": 48.785, + "args": { + "External id": 4723594,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359321311.436, "dur": 6.045, + "args": { + "External id": 4723595,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359321314.736, "dur": 2.257, + "args": { + "External id": 4723596,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321316.043, "dur": 0.831, + "args": { + "External id": 4723597,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359321318.299, "dur": 40.690, + "args": { + "External id": 4723598,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359321318.879, "dur": 39.536, + "args": { + "External id": 4723599,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359321363.323, "dur": 3.585, + "args": { + "External id": 4723600,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321365.001, "dur": 0.920, + "args": { + "External id": 4723601,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359321372.182, "dur": 1.329, + "args": { + "External id": 4723602,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359321383.360, "dur": 6.729, + "args": { + "External id": 4723603,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359321385.398, "dur": 4.434, + "args": { + "External id": 4723604,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359321471.804, "dur": 193.712, + "args": { + "External id": 4723605,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359321473.727, "dur": 2.679, + "args": { + "External id": 4723606,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359321480.088, "dur": 184.891, + "args": { + "External id": 4723607,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359321481.204, "dur": 0.451, + "args": { + "External id": 4723608,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359321482.743, "dur": 24.138, + "args": { + "External id": 4723609,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359321508.627, "dur": 5.366, + "args": { + "External id": 4723610,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321510.752, "dur": 2.815, + "args": { + "External id": 4723611,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359321517.431, "dur": 20.888, + "args": { + "External id": 4723612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359321518.463, "dur": 1.514, + "args": { + "External id": 4723613,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359321520.990, "dur": 17.069, + "args": { + "External id": 4723614,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321523.617, "dur": 2.342, + "args": { + "External id": 4723615,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359321539.550, "dur": 22.491, + "args": { + "External id": 4723616,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321563.643, "dur": 13.617, + "args": { + "External id": 4723617,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359321579.928, "dur": 14.702, + "args": { + "External id": 4723618,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321595.935, "dur": 13.316, + "args": { + "External id": 4723619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359321610.954, "dur": 25.180, + "args": { + "External id": 4723620,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321615.168, "dur": 1.600, + "args": { + "External id": 4723621,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321618.901, "dur": 3.002, + "args": { + "External id": 4723622,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321637.683, "dur": 13.253, + "args": { + "External id": 4723623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321652.080, "dur": 11.753, + "args": { + "External id": 4723624,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359321671.546, "dur": 1.409, + "args": { + "External id": 4723625,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359321680.498, "dur": 2.973, + "args": { + "External id": 4723626,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321682.332, "dur": 0.500, + "args": { + "External id": 4723627,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359321754.031, "dur": 71.677, + "args": { + "External id": 4723628,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359321829.704, "dur": 4.013, + "args": { + "External id": 4723629,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321831.915, "dur": 0.951, + "args": { + "External id": 4723630,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321835.090, "dur": 34.922, + "args": { + "External id": 4723631,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359321873.853, "dur": 6.947, + "args": { + "External id": 4723632,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359321874.862, "dur": 5.260, + "args": { + "External id": 4723633,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359321878.782, "dur": 1.153, + "args": { + "External id": 4723634,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359321882.928, "dur": 67.599, + "args": { + "External id": 4723635,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359321883.707, "dur": 66.366, + "args": { + "External id": 4723636,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359321953.725, "dur": 61.236, + "args": { + "External id": 4723637,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359322023.215, "dur": 4.722, + "args": { + "External id": 4723638,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322025.931, "dur": 1.005, + "args": { + "External id": 4723639,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359322031.481, "dur": 69.967, + "args": { + "External id": 4723640,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359322034.609, "dur": 3.567, + "args": { + "External id": 4723641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359322035.470, "dur": 2.201, + "args": { + "External id": 4723642,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322036.965, "dur": 0.582, + "args": { + "External id": 4723643,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359322038.716, "dur": 62.295, + "args": { + "External id": 4723644,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359322039.296, "dur": 60.693, + "args": { + "External id": 4723645,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359322106.557, "dur": 5.197, + "args": { + "External id": 4723646,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322109.129, "dur": 1.306, + "args": { + "External id": 4723647,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359322120.726, "dur": 1.464, + "args": { + "External id": 4723648,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359322129.604, "dur": 7.081, + "args": { + "External id": 4723649,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359322131.464, "dur": 4.944, + "args": { + "External id": 4723650,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359322220.986, "dur": 192.927, + "args": { + "External id": 4723651,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359322225.277, "dur": 2.434, + "args": { + "External id": 4723652,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359322231.220, "dur": 182.222, + "args": { + "External id": 4723653,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359322232.404, "dur": 0.497, + "args": { + "External id": 4723654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359322233.777, "dur": 23.435, + "args": { + "External id": 4723655,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359322258.954, "dur": 5.142, + "args": { + "External id": 4723656,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322262.810, "dur": 0.974, + "args": { + "External id": 4723657,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359322265.099, "dur": 22.817, + "args": { + "External id": 4723658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359322266.183, "dur": 1.561, + "args": { + "External id": 4723659,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359322268.799, "dur": 18.769, + "args": { + "External id": 4723660,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322271.680, "dur": 3.114, + "args": { + "External id": 4723661,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359322291.529, "dur": 21.125, + "args": { + "External id": 4723662,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322313.957, "dur": 14.426, + "args": { + "External id": 4723663,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359322330.986, "dur": 13.958, + "args": { + "External id": 4723664,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322346.120, "dur": 12.871, + "args": { + "External id": 4723665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359322360.678, "dur": 23.637, + "args": { + "External id": 4723666,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322364.709, "dur": 1.677, + "args": { + "External id": 4723667,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322368.824, "dur": 0.993, + "args": { + "External id": 4723668,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322388.016, "dur": 12.275, + "args": { + "External id": 4723669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322401.127, "dur": 11.323, + "args": { + "External id": 4723670,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359322419.775, "dur": 1.763, + "args": { + "External id": 4723671,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359322429.918, "dur": 3.370, + "args": { + "External id": 4723672,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322432.001, "dur": 0.479, + "args": { + "External id": 4723673,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359322496.171, "dur": 49.711, + "args": { + "External id": 4723674,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359322550.186, "dur": 4.200, + "args": { + "External id": 4723675,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322552.757, "dur": 0.798, + "args": { + "External id": 4723676,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322555.616, "dur": 22.892, + "args": { + "External id": 4723677,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359322584.660, "dur": 5.941, + "args": { + "External id": 4723678,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359322586.127, "dur": 3.792, + "args": { + "External id": 4723679,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322588.178, "dur": 1.548, + "args": { + "External id": 4723680,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359322593.020, "dur": 40.245, + "args": { + "External id": 4723681,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359322593.794, "dur": 38.847, + "args": { + "External id": 4723682,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322636.783, "dur": 14.501, + "args": { + "External id": 4723683,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359322656.244, "dur": 6.110, + "args": { + "External id": 4723684,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322660.758, "dur": 0.903, + "args": { + "External id": 4723685,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359322665.661, "dur": 48.975, + "args": { + "External id": 4723686,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359322666.375, "dur": 4.262, + "args": { + "External id": 4723687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359322667.203, "dur": 2.916, + "args": { + "External id": 4723688,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322669.220, "dur": 0.771, + "args": { + "External id": 4723689,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359322671.166, "dur": 43.086, + "args": { + "External id": 4723690,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359322674.272, "dur": 39.500, + "args": { + "External id": 4723691,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359322717.720, "dur": 3.487, + "args": { + "External id": 4723692,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322719.641, "dur": 0.613, + "args": { + "External id": 4723693,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359322726.453, "dur": 1.276, + "args": { + "External id": 4723694,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359322734.053, "dur": 5.473, + "args": { + "External id": 4723695,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359322735.626, "dur": 3.593, + "args": { + "External id": 4723696,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359322820.393, "dur": 338.493, + "args": { + "External id": 4723697,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359322824.402, "dur": 2.266, + "args": { + "External id": 4723698,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359322827.753, "dur": 330.470, + "args": { + "External id": 4723699,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359322828.823, "dur": 0.529, + "args": { + "External id": 4723700,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359322830.463, "dur": 20.277, + "args": { + "External id": 4723701,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359322852.248, "dur": 4.912, + "args": { + "External id": 4723702,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359322856.013, "dur": 0.872, + "args": { + "External id": 4723703,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359322858.288, "dur": 20.979, + "args": { + "External id": 4723704,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359322859.461, "dur": 1.711, + "args": { + "External id": 4723705,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359322862.336, "dur": 16.695, + "args": { + "External id": 4723706,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322864.716, "dur": 2.521, + "args": { + "External id": 4723707,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359322882.717, "dur": 20.835, + "args": { + "External id": 4723708,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322904.895, "dur": 14.465, + "args": { + "External id": 4723709,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359322922.075, "dur": 15.185, + "args": { + "External id": 4723710,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359322938.479, "dur": 13.031, + "args": { + "External id": 4723711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359322953.019, "dur": 172.989, + "args": { + "External id": 4723712,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323096.895, "dur": 4.148, + "args": { + "External id": 4723713,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323105.261, "dur": 0.852, + "args": { + "External id": 4723714,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323130.057, "dur": 13.214, + "args": { + "External id": 4723715,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323144.444, "dur": 12.331, + "args": { + "External id": 4723716,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359323167.724, "dur": 2.410, + "args": { + "External id": 4723717,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359323180.717, "dur": 3.938, + "args": { + "External id": 4723718,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323183.475, "dur": 0.356, + "args": { + "External id": 4723719,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359323262.679, "dur": 62.282, + "args": { + "External id": 4723720,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359323329.666, "dur": 6.590, + "args": { + "External id": 4723721,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323334.022, "dur": 1.050, + "args": { + "External id": 4723722,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323337.614, "dur": 24.428, + "args": { + "External id": 4723723,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359323366.812, "dur": 7.695, + "args": { + "External id": 4723724,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359323368.356, "dur": 5.502, + "args": { + "External id": 4723725,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323370.156, "dur": 3.427, + "args": { + "External id": 4723726,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359323377.292, "dur": 39.974, + "args": { + "External id": 4723727,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359323378.425, "dur": 38.217, + "args": { + "External id": 4723728,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323423.013, "dur": 15.467, + "args": { + "External id": 4723729,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359323444.000, "dur": 3.707, + "args": { + "External id": 4723730,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323445.891, "dur": 1.029, + "args": { + "External id": 4723731,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359323451.421, "dur": 56.358, + "args": { + "External id": 4723732,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359323452.207, "dur": 6.548, + "args": { + "External id": 4723733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359323453.133, "dur": 5.075, + "args": { + "External id": 4723734,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323457.077, "dur": 0.994, + "args": { + "External id": 4723735,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359323459.286, "dur": 48.149, + "args": { + "External id": 4723736,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359323459.767, "dur": 46.996, + "args": { + "External id": 4723737,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359323511.063, "dur": 3.368, + "args": { + "External id": 4723738,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323512.714, "dur": 0.701, + "args": { + "External id": 4723739,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359323519.542, "dur": 1.192, + "args": { + "External id": 4723740,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359323530.144, "dur": 7.110, + "args": { + "External id": 4723741,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359323532.036, "dur": 4.881, + "args": { + "External id": 4723742,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359323619.442, "dur": 187.944, + "args": { + "External id": 4723743,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359323621.645, "dur": 1.999, + "args": { + "External id": 4723744,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359323626.659, "dur": 180.232, + "args": { + "External id": 4723745,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359323627.613, "dur": 0.372, + "args": { + "External id": 4723746,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359323629.637, "dur": 21.553, + "args": { + "External id": 4723747,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359323654.954, "dur": 6.242, + "args": { + "External id": 4723748,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323657.070, "dur": 3.717, + "args": { + "External id": 4723749,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359323662.224, "dur": 21.715, + "args": { + "External id": 4723750,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359323662.941, "dur": 1.609, + "args": { + "External id": 4723751,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359323665.994, "dur": 17.648, + "args": { + "External id": 4723752,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323668.527, "dur": 2.325, + "args": { + "External id": 4723753,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359323685.335, "dur": 20.665, + "args": { + "External id": 4723754,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323707.597, "dur": 14.957, + "args": { + "External id": 4723755,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359323725.368, "dur": 14.346, + "args": { + "External id": 4723756,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323740.916, "dur": 13.158, + "args": { + "External id": 4723757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359323758.436, "dur": 22.029, + "args": { + "External id": 4723758,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323759.778, "dur": 1.625, + "args": { + "External id": 4723759,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323763.462, "dur": 3.283, + "args": { + "External id": 4723760,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323781.574, "dur": 12.209, + "args": { + "External id": 4723761,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323794.558, "dur": 11.286, + "args": { + "External id": 4723762,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359323812.699, "dur": 1.642, + "args": { + "External id": 4723763,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359323821.978, "dur": 3.511, + "args": { + "External id": 4723764,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323824.027, "dur": 0.494, + "args": { + "External id": 4723765,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359323888.576, "dur": 43.532, + "args": { + "External id": 4723766,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359323936.260, "dur": 3.933, + "args": { + "External id": 4723767,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323938.375, "dur": 0.984, + "args": { + "External id": 4723768,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359323941.377, "dur": 22.536, + "args": { + "External id": 4723769,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359323968.061, "dur": 7.744, + "args": { + "External id": 4723770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359323969.145, "dur": 6.019, + "args": { + "External id": 4723771,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359323973.321, "dur": 1.681, + "args": { + "External id": 4723772,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359323978.347, "dur": 82.368, + "args": { + "External id": 4723773,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359323979.494, "dur": 80.131, + "args": { + "External id": 4723774,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324080.413, "dur": 17.954, + "args": { + "External id": 4723775,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359324105.034, "dur": 4.420, + "args": { + "External id": 4723776,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324107.345, "dur": 1.016, + "args": { + "External id": 4723777,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359324113.342, "dur": 51.419, + "args": { + "External id": 4723778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359324116.598, "dur": 3.491, + "args": { + "External id": 4723779,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359324117.422, "dur": 2.165, + "args": { + "External id": 4723780,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324118.833, "dur": 0.632, + "args": { + "External id": 4723781,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359324120.836, "dur": 43.550, + "args": { + "External id": 4723782,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359324121.605, "dur": 42.239, + "args": { + "External id": 4723783,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359324168.395, "dur": 3.645, + "args": { + "External id": 4723784,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324170.109, "dur": 0.955, + "args": { + "External id": 4723785,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359324177.675, "dur": 1.435, + "args": { + "External id": 4723786,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359324188.441, "dur": 6.572, + "args": { + "External id": 4723787,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359324190.339, "dur": 4.373, + "args": { + "External id": 4723788,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359324275.481, "dur": 202.517, + "args": { + "External id": 4723789,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359324280.116, "dur": 1.879, + "args": { + "External id": 4723790,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359324283.187, "dur": 194.290, + "args": { + "External id": 4723791,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359324284.416, "dur": 0.375, + "args": { + "External id": 4723792,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359324287.990, "dur": 21.403, + "args": { + "External id": 4723793,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359324310.829, "dur": 5.843, + "args": { + "External id": 4723794,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324315.694, "dur": 0.729, + "args": { + "External id": 4723795,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359324326.570, "dur": 22.715, + "args": { + "External id": 4723796,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359324327.294, "dur": 1.538, + "args": { + "External id": 4723797,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359324330.293, "dur": 18.474, + "args": { + "External id": 4723798,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324332.666, "dur": 2.598, + "args": { + "External id": 4723799,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359324350.782, "dur": 20.978, + "args": { + "External id": 4723800,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324373.168, "dur": 16.122, + "args": { + "External id": 4723801,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359324392.541, "dur": 15.727, + "args": { + "External id": 4723802,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324411.861, "dur": 12.532, + "args": { + "External id": 4723803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359324426.159, "dur": 20.798, + "args": { + "External id": 4723804,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324427.724, "dur": 1.915, + "args": { + "External id": 4723805,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324431.522, "dur": 0.989, + "args": { + "External id": 4723806,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324448.432, "dur": 13.453, + "args": { + "External id": 4723807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324462.874, "dur": 11.423, + "args": { + "External id": 4723808,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359324483.346, "dur": 1.474, + "args": { + "External id": 4723809,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359324491.643, "dur": 3.233, + "args": { + "External id": 4723810,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324493.904, "dur": 0.305, + "args": { + "External id": 4723811,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359324551.852, "dur": 45.511, + "args": { + "External id": 4723812,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359324601.754, "dur": 3.880, + "args": { + "External id": 4723813,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324603.701, "dur": 1.127, + "args": { + "External id": 4723814,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324610.393, "dur": 22.872, + "args": { + "External id": 4723815,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359324639.619, "dur": 6.652, + "args": { + "External id": 4723816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359324640.837, "dur": 4.800, + "args": { + "External id": 4723817,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324642.566, "dur": 2.886, + "args": { + "External id": 4723818,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359324648.537, "dur": 37.510, + "args": { + "External id": 4723819,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359324649.627, "dur": 35.748, + "args": { + "External id": 4723820,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324689.276, "dur": 14.318, + "args": { + "External id": 4723821,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359324708.170, "dur": 5.169, + "args": { + "External id": 4723822,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324712.271, "dur": 0.483, + "args": { + "External id": 4723823,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359324716.399, "dur": 48.140, + "args": { + "External id": 4723824,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359324717.224, "dur": 3.604, + "args": { + "External id": 4723825,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359324718.050, "dur": 2.284, + "args": { + "External id": 4723826,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324719.465, "dur": 0.764, + "args": { + "External id": 4723827,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359324721.543, "dur": 42.654, + "args": { + "External id": 4723828,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359324725.121, "dur": 38.531, + "args": { + "External id": 4723829,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359324767.724, "dur": 3.239, + "args": { + "External id": 4723830,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324769.185, "dur": 0.868, + "args": { + "External id": 4723831,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359324775.464, "dur": 1.215, + "args": { + "External id": 4723832,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359324782.691, "dur": 8.098, + "args": { + "External id": 4723833,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359324786.601, "dur": 3.951, + "args": { + "External id": 4723834,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359324859.312, "dur": 239.581, + "args": { + "External id": 4723835,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359324861.183, "dur": 2.284, + "args": { + "External id": 4723836,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359324866.450, "dur": 231.932, + "args": { + "External id": 4723837,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359324867.431, "dur": 0.267, + "args": { + "External id": 4723838,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359324868.624, "dur": 19.462, + "args": { + "External id": 4723839,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359324889.620, "dur": 5.144, + "args": { + "External id": 4723840,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359324891.955, "dur": 2.597, + "args": { + "External id": 4723841,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359324895.864, "dur": 22.437, + "args": { + "External id": 4723842,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359324898.890, "dur": 1.438, + "args": { + "External id": 4723843,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359324901.473, "dur": 16.579, + "args": { + "External id": 4723844,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324903.803, "dur": 2.423, + "args": { + "External id": 4723845,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359324920.064, "dur": 19.212, + "args": { + "External id": 4723846,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324940.357, "dur": 13.717, + "args": { + "External id": 4723847,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359324956.807, "dur": 13.328, + "args": { + "External id": 4723848,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359324971.159, "dur": 49.967, + "args": { + "External id": 4723849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359325024.449, "dur": 27.946, + "args": { + "External id": 4723850,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325025.969, "dur": 2.019, + "args": { + "External id": 4723851,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325032.877, "dur": 2.668, + "args": { + "External id": 4723852,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325053.800, "dur": 26.503, + "args": { + "External id": 4723853,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325082.145, "dur": 14.563, + "args": { + "External id": 4723854,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359325106.261, "dur": 2.367, + "args": { + "External id": 4723855,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359325118.204, "dur": 3.983, + "args": { + "External id": 4723856,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325120.789, "dur": 0.467, + "args": { + "External id": 4723857,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359325191.711, "dur": 55.351, + "args": { + "External id": 4723858,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359325251.355, "dur": 6.630, + "args": { + "External id": 4723859,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325255.959, "dur": 1.311, + "args": { + "External id": 4723860,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325259.170, "dur": 22.410, + "args": { + "External id": 4723861,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359325285.615, "dur": 5.614, + "args": { + "External id": 4723862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359325286.963, "dur": 3.655, + "args": { + "External id": 4723863,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325288.802, "dur": 1.564, + "args": { + "External id": 4723864,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359325293.899, "dur": 42.123, + "args": { + "External id": 4723865,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359325297.122, "dur": 38.256, + "args": { + "External id": 4723866,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325339.440, "dur": 15.989, + "args": { + "External id": 4723867,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359325359.645, "dur": 25.784, + "args": { + "External id": 4723868,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359325362.163, "dur": 22.900, + "args": { + "External id": 4723869,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325367.275, "dur": 0.964, + "args": { + "External id": 4723870,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359325390.276, "dur": 26.001, + "args": { + "External id": 4723871,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359325392.149, "dur": 23.924, + "args": { + "External id": 4723872,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 9527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325396.401, "dur": 3.942, + "args": { + "External id": 4723873,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325401.521, "dur": 14.106, + "args": { + "External id": 4723874,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359325429.009, "dur": 6.838, + "args": { + "External id": 4723875,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359325433.179, "dur": 2.375, + "args": { + "External id": 4723876,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359325436.899, "dur": 1.516, + "args": { + "External id": 4723877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359325437.625, "dur": 0.507, + "args": { + "External id": 4723878,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325476.998, "dur": 21.329, + "args": { + "External id": 4723879,"Sequence number": 47018976, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325499.962, "dur": 14.266, + "args": { + "External id": 4723880,"Sequence number": 47018977, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9535 + } + }, + { + "ph": "s", "id": 16, "pid": 1336753, "tid": 1336753, "ts": 1712359325499.962, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359325519.495, "dur": 5.585, + "args": { + "External id": 4723881,"Sequence number": 47018978, "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": [[16, 4, 4096], [], [], [], []], "Ev Idx": 9536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325522.977, "dur": 0.978, + "args": { + "External id": 4723882,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1712359325530.101, "dur": 6.057, + "args": { + "External id": 4723883,"Sequence number": 47018978, "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": [[16, 4, 4096], [], []], "Ev Idx": 9538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325534.094, "dur": 0.880, + "args": { + "External id": 4723884,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359325537.402, "dur": 3.480, + "args": { + "External id": 4723885,"Sequence number": 47018978, "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": [[16, 4096], [], [], [], []], "Ev Idx": 9540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325539.147, "dur": 1.147, + "args": { + "External id": 4723886,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 9541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359325544.523, "dur": 8.225, + "args": { + "External id": 4723887,"Sequence number": 47018978, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9542 + } + }, + { + "ph": "s", "id": 15, "pid": 1336753, "tid": 1336753, "ts": 1712359325544.523, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325550.189, "dur": 1.063, + "args": { + "External id": 4723888,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359325553.762, "dur": 6.002, + "args": { + "External id": 4723889,"Sequence number": 47018979, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9544 + } + }, + { + "ph": "s", "id": 14, "pid": 1336753, "tid": 1336753, "ts": 1712359325553.762, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325557.995, "dur": 0.983, + "args": { + "External id": 4723890,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1712359325560.767, "dur": 7.527, + "args": { + "External id": 4723891,"Sequence number": 47018980, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 9546 + } + }, + { + "ph": "s", "id": 13, "pid": 1336753, "tid": 1336753, "ts": 1712359325560.767, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325566.388, "dur": 1.022, + "args": { + "External id": 4723892,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359325569.326, "dur": 4.742, + "args": { + "External id": 4723893,"Sequence number": 47018981, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 9548 + } + }, + { + "ph": "s", "id": 12, "pid": 1336753, "tid": 1336753, "ts": 1712359325569.326, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325571.976, "dur": 1.357, + "args": { + "External id": 4723894,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 9549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1712359325577.608, "dur": 28.449, + "args": { + "External id": 4723895,"Sequence number": 47018982, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712359325579.263, "dur": 26.587, + "args": { + "External id": 4723896,"Sequence number": 47018982, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359325581.947, "dur": 5.587, + "args": { + "External id": 4723897,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 9552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359325583.993, "dur": 3.039, + "args": { + "External id": 4723898,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325588.339, "dur": 16.962, + "args": { + "External id": 4723899,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 9554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359325630.771, "dur": 6.719, + "args": { + "External id": 4723900,"Sequence number": 47018982, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 9555 + } + }, + { + "ph": "s", "id": 11, "pid": 1336753, "tid": 1336753, "ts": 1712359325630.771, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359325639.969, "dur": 1.197, + "args": { + "External id": 4723901,"Sequence number": 47018983, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359325673.668, "dur": 44244.618, + "args": { + "External id": 4723902,"Sequence number": 47018983, "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": [[8192, 1], [1], [2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536], [32000, 2048], [], [], [], [], []], "Ev Idx": 9557 + } + }, + { + "ph": "s", "id": 10, "pid": 1336753, "tid": 1336753, "ts": 1712359325673.668, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1712359325687.664, "dur": 25.563, + "args": { + "External id": 4723903,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712359325688.501, "dur": 24.551, + "args": { + "External id": 4723904,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359325689.743, "dur": 5.543, + "args": { + "External id": 4723905,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359325691.254, "dur": 3.644, + "args": { + "External id": 4723906,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325696.161, "dur": 16.449, + "args": { + "External id": 4723907,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [8192, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 9562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359325727.399, "dur": 26.127, + "args": { + "External id": 4723908,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359325728.873, "dur": 5.736, + "args": { + "External id": 4723909,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325730.932, "dur": 3.371, + "args": { + "External id": 4723910,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325735.865, "dur": 17.433, + "args": { + "External id": 4723911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325738.036, "dur": 14.729, + "args": { + "External id": 4723912,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359325756.750, "dur": 21.483, + "args": { + "External id": 4723913,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359325757.455, "dur": 6.757, + "args": { + "External id": 4723914,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325760.888, "dur": 3.045, + "args": { + "External id": 4723915,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325765.165, "dur": 12.880, + "args": { + "External id": 4723916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325765.717, "dur": 12.051, + "args": { + "External id": 4723917,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 9572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1712359325783.415, "dur": 20.169, + "args": { + "External id": 4723918,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359325787.629, "dur": 2.800, + "args": { + "External id": 4723919,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325791.048, "dur": 12.279, + "args": { + "External id": 4723920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 9575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325791.681, "dur": 11.360, + "args": { + "External id": 4723921,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1712359325810.815, "dur": 20.979, + "args": { + "External id": 4723922,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359325834.296, "dur": 47.897, + "args": { + "External id": 4723923,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359325836.179, "dur": 45.521, + "args": { + "External id": 4723924,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325840.671, "dur": 0.885, + "args": { + "External id": 4723925,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359325842.773, "dur": 23.857, + "args": { + "External id": 4723926,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359325844.013, "dur": 22.371, + "args": { + "External id": 4723927,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 9582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359325848.212, "dur": 3.370, + "args": { + "External id": 4723928,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359325852.558, "dur": 13.513, + "args": { + "External id": 4723929,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 9584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1712359325885.763, "dur": 38323.087, + "args": { + "External id": 4723930,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1712359325887.462, "dur": 38320.157, + "args": { + "External id": 4723931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359364220.213, "dur": 8.736, + "args": { + "External id": 4723932,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364226.209, "dur": 0.955, + "args": { + "External id": 4723933,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359364233.437, "dur": 98.620, + "args": { + "External id": 4723934,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359364234.940, "dur": 6.145, + "args": { + "External id": 4723935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359364237.072, "dur": 3.252, + "args": { + "External id": 4723936,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364239.064, "dur": 1.013, + "args": { + "External id": 4723937,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359364242.330, "dur": 89.077, + "args": { + "External id": 4723938,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359364246.367, "dur": 84.296, + "args": { + "External id": 4723939,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359364335.304, "dur": 4.080, + "args": { + "External id": 4723940,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364337.353, "dur": 0.707, + "args": { + "External id": 4723941,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359364345.735, "dur": 2.972, + "args": { + "External id": 4723942,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359364357.210, "dur": 6.954, + "args": { + "External id": 4723943,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359364359.795, "dur": 4.078, + "args": { + "External id": 4723944,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359364488.026, "dur": 205.576, + "args": { + "External id": 4723945,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359364490.984, "dur": 2.351, + "args": { + "External id": 4723946,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359364497.309, "dur": 195.853, + "args": { + "External id": 4723947,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359364498.657, "dur": 0.657, + "args": { + "External id": 4723948,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359364500.750, "dur": 24.779, + "args": { + "External id": 4723949,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359364527.133, "dur": 5.526, + "args": { + "External id": 4723950,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364529.566, "dur": 2.709, + "args": { + "External id": 4723951,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359364533.589, "dur": 27.776, + "args": { + "External id": 4723952,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359364534.679, "dur": 1.458, + "args": { + "External id": 4723953,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359364540.107, "dur": 20.941, + "args": { + "External id": 4723954,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359364543.774, "dur": 3.549, + "args": { + "External id": 4723955,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359364563.006, "dur": 22.994, + "args": { + "External id": 4723956,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359364587.814, "dur": 15.949, + "args": { + "External id": 4723957,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359364606.546, "dur": 16.478, + "args": { + "External id": 4723958,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359364624.589, "dur": 14.564, + "args": { + "External id": 4723959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359364640.947, "dur": 23.793, + "args": { + "External id": 4723960,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359364643.265, "dur": 1.896, + "args": { + "External id": 4723961,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364649.683, "dur": 0.630, + "args": { + "External id": 4723962,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359364666.045, "dur": 13.246, + "args": { + "External id": 4723963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359364680.466, "dur": 11.746, + "args": { + "External id": 4723964,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359364699.789, "dur": 1.831, + "args": { + "External id": 4723965,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359364707.669, "dur": 3.800, + "args": { + "External id": 4723966,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364709.705, "dur": 0.950, + "args": { + "External id": 4723967,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359364776.143, "dur": 57.301, + "args": { + "External id": 4723968,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359364837.822, "dur": 9.410, + "args": { + "External id": 4723969,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364842.147, "dur": 2.985, + "args": { + "External id": 4723970,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359364848.747, "dur": 24.141, + "args": { + "External id": 4723971,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359364877.566, "dur": 5.797, + "args": { + "External id": 4723972,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359364879.168, "dur": 3.541, + "args": { + "External id": 4723973,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364881.130, "dur": 1.218, + "args": { + "External id": 4723974,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359364886.256, "dur": 44.902, + "args": { + "External id": 4723975,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359364889.406, "dur": 41.220, + "args": { + "External id": 4723976,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359364935.372, "dur": 15.156, + "args": { + "External id": 4723977,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359364956.133, "dur": 3.941, + "args": { + "External id": 4723978,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364958.483, "dur": 0.683, + "args": { + "External id": 4723979,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359364964.123, "dur": 91.050, + "args": { + "External id": 4723980,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359364964.905, "dur": 5.962, + "args": { + "External id": 4723981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359364965.711, "dur": 4.678, + "args": { + "External id": 4723982,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359364969.182, "dur": 1.059, + "args": { + "External id": 4723983,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359364971.502, "dur": 83.157, + "args": { + "External id": 4723984,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359364972.347, "dur": 81.357, + "args": { + "External id": 4723985,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359365061.121, "dur": 18.627, + "args": { + "External id": 4723986,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365076.408, "dur": 1.387, + "args": { + "External id": 4723987,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359365088.084, "dur": 1.726, + "args": { + "External id": 4723988,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359365099.844, "dur": 7.027, + "args": { + "External id": 4723989,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359365101.526, "dur": 5.078, + "args": { + "External id": 4723990,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359365205.681, "dur": 198.320, + "args": { + "External id": 4723991,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359365207.792, "dur": 3.973, + "args": { + "External id": 4723992,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359365213.149, "dur": 190.322, + "args": { + "External id": 4723993,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359365214.486, "dur": 0.579, + "args": { + "External id": 4723994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359365218.298, "dur": 24.013, + "args": { + "External id": 4723995,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359365244.027, "dur": 5.627, + "args": { + "External id": 4723996,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365248.455, "dur": 0.909, + "args": { + "External id": 4723997,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359365250.663, "dur": 23.477, + "args": { + "External id": 4723998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359365251.918, "dur": 1.452, + "args": { + "External id": 4723999,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359365254.745, "dur": 19.069, + "args": { + "External id": 4724000,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365257.297, "dur": 2.994, + "args": { + "External id": 4724001,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359365275.548, "dur": 23.129, + "args": { + "External id": 4724002,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365300.164, "dur": 14.507, + "args": { + "External id": 4724003,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359365317.479, "dur": 15.080, + "args": { + "External id": 4724004,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365336.636, "dur": 13.491, + "args": { + "External id": 4724005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359365351.807, "dur": 23.137, + "args": { + "External id": 4724006,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365353.494, "dur": 1.834, + "args": { + "External id": 4724007,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365357.860, "dur": 2.884, + "args": { + "External id": 4724008,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365376.417, "dur": 12.746, + "args": { + "External id": 4724009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365390.271, "dur": 12.056, + "args": { + "External id": 4724010,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359365412.689, "dur": 1.813, + "args": { + "External id": 4724011,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359365423.061, "dur": 3.734, + "args": { + "External id": 4724012,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365425.571, "dur": 0.452, + "args": { + "External id": 4724013,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359365489.601, "dur": 53.055, + "args": { + "External id": 4724014,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359365547.315, "dur": 4.518, + "args": { + "External id": 4724015,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365550.035, "dur": 0.868, + "args": { + "External id": 4724016,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365553.165, "dur": 27.311, + "args": { + "External id": 4724017,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359365584.581, "dur": 7.866, + "args": { + "External id": 4724018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359365585.861, "dur": 5.848, + "args": { + "External id": 4724019,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365590.203, "dur": 1.303, + "args": { + "External id": 4724020,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359365595.074, "dur": 39.380, + "args": { + "External id": 4724021,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359365596.042, "dur": 37.787, + "args": { + "External id": 4724022,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365638.267, "dur": 14.897, + "args": { + "External id": 4724023,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359365658.201, "dur": 3.690, + "args": { + "External id": 4724024,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365660.077, "dur": 1.016, + "args": { + "External id": 4724025,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359365667.859, "dur": 46.243, + "args": { + "External id": 4724026,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359365668.524, "dur": 3.672, + "args": { + "External id": 4724027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359365669.481, "dur": 2.215, + "args": { + "External id": 4724028,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365670.958, "dur": 0.586, + "args": { + "External id": 4724029,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359365672.868, "dur": 40.830, + "args": { + "External id": 4724030,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359365673.429, "dur": 39.626, + "args": { + "External id": 4724031,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359365735.684, "dur": 4.292, + "args": { + "External id": 4724032,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365738.070, "dur": 0.891, + "args": { + "External id": 4724033,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359365747.294, "dur": 1.197, + "args": { + "External id": 4724034,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359365755.586, "dur": 7.522, + "args": { + "External id": 4724035,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359365757.188, "dur": 5.630, + "args": { + "External id": 4724036,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359365840.385, "dur": 241.499, + "args": { + "External id": 4724037,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359365842.154, "dur": 2.391, + "args": { + "External id": 4724038,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359365845.848, "dur": 235.423, + "args": { + "External id": 4724039,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359365847.021, "dur": 0.371, + "args": { + "External id": 4724040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359365851.481, "dur": 23.002, + "args": { + "External id": 4724041,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359365876.002, "dur": 3.177, + "args": { + "External id": 4724042,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359365878.186, "dur": 0.799, + "args": { + "External id": 4724043,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359365879.986, "dur": 22.764, + "args": { + "External id": 4724044,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359365880.725, "dur": 1.898, + "args": { + "External id": 4724045,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359365883.666, "dur": 18.784, + "args": { + "External id": 4724046,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365888.055, "dur": 2.247, + "args": { + "External id": 4724047,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359365904.152, "dur": 19.067, + "args": { + "External id": 4724048,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365924.548, "dur": 13.571, + "args": { + "External id": 4724049,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359365940.676, "dur": 16.814, + "args": { + "External id": 4724050,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365960.948, "dur": 12.118, + "args": { + "External id": 4724051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359365975.123, "dur": 63.522, + "args": { + "External id": 4724052,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359365976.550, "dur": 1.834, + "args": { + "External id": 4724053,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366019.000, "dur": 1.112, + "args": { + "External id": 4724054,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366040.666, "dur": 12.759, + "args": { + "External id": 4724055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366054.534, "dur": 24.569, + "args": { + "External id": 4724056,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359366093.114, "dur": 2.147, + "args": { + "External id": 4724057,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359366104.562, "dur": 3.844, + "args": { + "External id": 4724058,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366107.058, "dur": 0.477, + "args": { + "External id": 4724059,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359366177.463, "dur": 69.238, + "args": { + "External id": 4724060,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359366250.899, "dur": 4.496, + "args": { + "External id": 4724061,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366253.093, "dur": 1.184, + "args": { + "External id": 4724062,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366256.693, "dur": 30.875, + "args": { + "External id": 4724063,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359366291.852, "dur": 8.313, + "args": { + "External id": 4724064,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359366296.347, "dur": 3.185, + "args": { + "External id": 4724065,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366298.492, "dur": 0.805, + "args": { + "External id": 4724066,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359366317.469, "dur": 68.283, + "args": { + "External id": 4724067,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359366318.629, "dur": 66.422, + "args": { + "External id": 4724068,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366389.735, "dur": 26.514, + "args": { + "External id": 4724069,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359366421.640, "dur": 5.944, + "args": { + "External id": 4724070,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366425.656, "dur": 1.073, + "args": { + "External id": 4724071,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359366431.211, "dur": 50.125, + "args": { + "External id": 4724072,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359366432.226, "dur": 5.970, + "args": { + "External id": 4724073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359366433.208, "dur": 4.417, + "args": { + "External id": 4724074,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366434.417, "dur": 3.048, + "args": { + "External id": 4724075,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359366438.945, "dur": 41.734, + "args": { + "External id": 4724076,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359366439.498, "dur": 40.703, + "args": { + "External id": 4724077,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359366487.157, "dur": 4.070, + "args": { + "External id": 4724078,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366489.193, "dur": 0.784, + "args": { + "External id": 4724079,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359366496.749, "dur": 1.290, + "args": { + "External id": 4724080,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359366505.477, "dur": 6.674, + "args": { + "External id": 4724081,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359366507.455, "dur": 4.427, + "args": { + "External id": 4724082,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359366594.264, "dur": 189.037, + "args": { + "External id": 4724083,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359366596.977, "dur": 2.087, + "args": { + "External id": 4724084,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359366600.433, "dur": 182.461, + "args": { + "External id": 4724085,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359366601.409, "dur": 0.386, + "args": { + "External id": 4724086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359366605.791, "dur": 22.145, + "args": { + "External id": 4724087,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359366629.518, "dur": 3.504, + "args": { + "External id": 4724088,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366632.011, "dur": 0.790, + "args": { + "External id": 4724089,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359366633.950, "dur": 25.803, + "args": { + "External id": 4724090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359366634.954, "dur": 3.451, + "args": { + "External id": 4724091,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359366642.066, "dur": 17.315, + "args": { + "External id": 4724092,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366644.836, "dur": 2.594, + "args": { + "External id": 4724093,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359366661.092, "dur": 21.423, + "args": { + "External id": 4724094,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366683.717, "dur": 13.840, + "args": { + "External id": 4724095,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359366700.075, "dur": 14.720, + "args": { + "External id": 4724096,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366716.231, "dur": 13.459, + "args": { + "External id": 4724097,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359366731.510, "dur": 23.561, + "args": { + "External id": 4724098,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366733.058, "dur": 1.829, + "args": { + "External id": 4724099,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366739.552, "dur": 1.012, + "args": { + "External id": 4724100,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366756.385, "dur": 13.157, + "args": { + "External id": 4724101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366770.754, "dur": 11.062, + "args": { + "External id": 4724102,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359366788.906, "dur": 1.547, + "args": { + "External id": 4724103,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359366798.326, "dur": 3.455, + "args": { + "External id": 4724104,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366800.730, "dur": 0.373, + "args": { + "External id": 4724105,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359366859.537, "dur": 44.558, + "args": { + "External id": 4724106,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359366908.319, "dur": 5.982, + "args": { + "External id": 4724107,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366912.502, "dur": 0.926, + "args": { + "External id": 4724108,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359366915.466, "dur": 22.389, + "args": { + "External id": 4724109,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359366941.487, "dur": 6.589, + "args": { + "External id": 4724110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359366942.603, "dur": 4.802, + "args": { + "External id": 4724111,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359366944.453, "dur": 2.739, + "args": { + "External id": 4724112,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359366950.091, "dur": 90.389, + "args": { + "External id": 4724113,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359366951.145, "dur": 88.435, + "args": { + "External id": 4724114,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367048.348, "dur": 31.767, + "args": { + "External id": 4724115,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359367088.277, "dur": 4.872, + "args": { + "External id": 4724116,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367091.178, "dur": 0.839, + "args": { + "External id": 4724117,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359367097.577, "dur": 55.922, + "args": { + "External id": 4724118,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359367098.470, "dur": 7.224, + "args": { + "External id": 4724119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359367099.705, "dur": 5.300, + "args": { + "External id": 4724120,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367103.897, "dur": 0.981, + "args": { + "External id": 4724121,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359367106.795, "dur": 46.347, + "args": { + "External id": 4724122,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359367107.481, "dur": 45.015, + "args": { + "External id": 4724123,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359367177.387, "dur": 4.160, + "args": { + "External id": 4724124,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367179.589, "dur": 0.783, + "args": { + "External id": 4724125,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359367188.353, "dur": 1.211, + "args": { + "External id": 4724126,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359367196.997, "dur": 10.813, + "args": { + "External id": 4724127,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359367201.277, "dur": 6.240, + "args": { + "External id": 4724128,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359367293.705, "dur": 190.485, + "args": { + "External id": 4724129,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359367295.823, "dur": 2.545, + "args": { + "External id": 4724130,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359367299.647, "dur": 184.126, + "args": { + "External id": 4724131,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359367301.060, "dur": 0.355, + "args": { + "External id": 4724132,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359367302.441, "dur": 24.253, + "args": { + "External id": 4724133,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359367328.043, "dur": 3.958, + "args": { + "External id": 4724134,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367330.349, "dur": 1.213, + "args": { + "External id": 4724135,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359367333.191, "dur": 28.355, + "args": { + "External id": 4724136,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359367333.978, "dur": 1.495, + "args": { + "External id": 4724137,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359367339.647, "dur": 21.522, + "args": { + "External id": 4724138,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367344.981, "dur": 2.858, + "args": { + "External id": 4724139,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359367362.690, "dur": 20.651, + "args": { + "External id": 4724140,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367384.833, "dur": 14.419, + "args": { + "External id": 4724141,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359367402.003, "dur": 14.550, + "args": { + "External id": 4724142,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367418.000, "dur": 13.003, + "args": { + "External id": 4724143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359367432.711, "dur": 23.602, + "args": { + "External id": 4724144,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367434.137, "dur": 1.630, + "args": { + "External id": 4724145,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367441.082, "dur": 0.826, + "args": { + "External id": 4724146,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367457.587, "dur": 12.696, + "args": { + "External id": 4724147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367471.252, "dur": 11.505, + "args": { + "External id": 4724148,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359367489.835, "dur": 1.466, + "args": { + "External id": 4724149,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359367498.683, "dur": 3.292, + "args": { + "External id": 4724150,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367500.939, "dur": 0.302, + "args": { + "External id": 4724151,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359367560.300, "dur": 47.862, + "args": { + "External id": 4724152,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359367612.474, "dur": 6.967, + "args": { + "External id": 4724153,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367616.924, "dur": 1.493, + "args": { + "External id": 4724154,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367620.746, "dur": 24.453, + "args": { + "External id": 4724155,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359367648.921, "dur": 5.142, + "args": { + "External id": 4724156,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359367650.455, "dur": 3.037, + "args": { + "External id": 4724157,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367652.276, "dur": 1.005, + "args": { + "External id": 4724158,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359367656.131, "dur": 40.681, + "args": { + "External id": 4724159,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359367659.171, "dur": 37.072, + "args": { + "External id": 4724160,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367700.387, "dur": 14.811, + "args": { + "External id": 4724161,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359367720.008, "dur": 3.400, + "args": { + "External id": 4724162,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367721.895, "dur": 0.804, + "args": { + "External id": 4724163,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359367726.814, "dur": 89.726, + "args": { + "External id": 4724164,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359367762.680, "dur": 9.947, + "args": { + "External id": 4724165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359367766.942, "dur": 5.147, + "args": { + "External id": 4724166,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367769.105, "dur": 2.800, + "args": { + "External id": 4724167,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359367773.479, "dur": 42.723, + "args": { + "External id": 4724168,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359367774.157, "dur": 41.546, + "args": { + "External id": 4724169,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359367820.455, "dur": 3.679, + "args": { + "External id": 4724170,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367822.410, "dur": 0.754, + "args": { + "External id": 4724171,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359367831.425, "dur": 1.255, + "args": { + "External id": 4724172,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359367839.370, "dur": 5.805, + "args": { + "External id": 4724173,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359367841.200, "dur": 3.679, + "args": { + "External id": 4724174,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359367921.413, "dur": 257.251, + "args": { + "External id": 4724175,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359367923.596, "dur": 2.016, + "args": { + "External id": 4724176,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359367926.612, "dur": 251.493, + "args": { + "External id": 4724177,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359367930.589, "dur": 0.308, + "args": { + "External id": 4724178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359367934.734, "dur": 21.345, + "args": { + "External id": 4724179,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359367957.517, "dur": 3.584, + "args": { + "External id": 4724180,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359367959.611, "dur": 1.170, + "args": { + "External id": 4724181,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359367962.149, "dur": 65.558, + "args": { + "External id": 4724182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359367963.309, "dur": 3.406, + "args": { + "External id": 4724183,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359367967.799, "dur": 58.913, + "args": { + "External id": 4724184,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359367970.321, "dur": 2.281, + "args": { + "External id": 4724185,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359368029.860, "dur": 24.745, + "args": { + "External id": 4724186,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368056.052, "dur": 26.841, + "args": { + "External id": 4724187,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359368089.235, "dur": 17.567, + "args": { + "External id": 4724188,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368108.114, "dur": 13.488, + "args": { + "External id": 4724189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359368123.788, "dur": 23.029, + "args": { + "External id": 4724190,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368125.902, "dur": 2.336, + "args": { + "External id": 4724191,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368130.668, "dur": 0.931, + "args": { + "External id": 4724192,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368148.368, "dur": 12.807, + "args": { + "External id": 4724193,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368164.899, "dur": 11.943, + "args": { + "External id": 4724194,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359368186.160, "dur": 2.122, + "args": { + "External id": 4724195,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359368197.863, "dur": 3.665, + "args": { + "External id": 4724196,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368200.377, "dur": 0.294, + "args": { + "External id": 4724197,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359368267.927, "dur": 56.423, + "args": { + "External id": 4724198,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359368328.807, "dur": 4.300, + "args": { + "External id": 4724199,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368331.043, "dur": 1.108, + "args": { + "External id": 4724200,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368334.403, "dur": 25.755, + "args": { + "External id": 4724201,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359368364.299, "dur": 9.966, + "args": { + "External id": 4724202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359368367.929, "dur": 5.469, + "args": { + "External id": 4724203,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368369.773, "dur": 3.418, + "args": { + "External id": 4724204,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359368377.135, "dur": 45.886, + "args": { + "External id": 4724205,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359368377.991, "dur": 44.366, + "args": { + "External id": 4724206,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368426.976, "dur": 15.244, + "args": { + "External id": 4724207,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359368447.442, "dur": 4.931, + "args": { + "External id": 4724208,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368451.153, "dur": 0.452, + "args": { + "External id": 4724209,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359368456.024, "dur": 46.779, + "args": { + "External id": 4724210,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359368456.906, "dur": 3.627, + "args": { + "External id": 4724211,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359368457.809, "dur": 2.224, + "args": { + "External id": 4724212,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368459.266, "dur": 0.632, + "args": { + "External id": 4724213,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359368461.216, "dur": 41.138, + "args": { + "External id": 4724214,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359368461.715, "dur": 40.060, + "args": { + "External id": 4724215,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359368506.684, "dur": 3.865, + "args": { + "External id": 4724216,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368508.417, "dur": 0.972, + "args": { + "External id": 4724217,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359368517.700, "dur": 1.342, + "args": { + "External id": 4724218,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359368525.488, "dur": 6.231, + "args": { + "External id": 4724219,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359368527.501, "dur": 3.973, + "args": { + "External id": 4724220,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359368608.197, "dur": 278.829, + "args": { + "External id": 4724221,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359368610.128, "dur": 2.282, + "args": { + "External id": 4724222,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359368618.150, "dur": 268.369, + "args": { + "External id": 4724223,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359368619.600, "dur": 0.253, + "args": { + "External id": 4724224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359368707.499, "dur": 23.535, + "args": { + "External id": 4724225,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359368732.709, "dur": 5.483, + "args": { + "External id": 4724226,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368735.238, "dur": 2.670, + "args": { + "External id": 4724227,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359368739.223, "dur": 22.237, + "args": { + "External id": 4724228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359368739.937, "dur": 1.518, + "args": { + "External id": 4724229,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359368742.576, "dur": 18.560, + "args": { + "External id": 4724230,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368745.049, "dur": 2.278, + "args": { + "External id": 4724231,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359368762.769, "dur": 20.308, + "args": { + "External id": 4724232,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368784.390, "dur": 15.290, + "args": { + "External id": 4724233,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359368804.696, "dur": 14.523, + "args": { + "External id": 4724234,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368820.344, "dur": 13.082, + "args": { + "External id": 4724235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359368835.234, "dur": 21.452, + "args": { + "External id": 4724236,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368836.275, "dur": 1.642, + "args": { + "External id": 4724237,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368840.016, "dur": 2.810, + "args": { + "External id": 4724238,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368857.849, "dur": 13.190, + "args": { + "External id": 4724239,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359368874.358, "dur": 11.240, + "args": { + "External id": 4724240,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359368893.356, "dur": 1.457, + "args": { + "External id": 4724241,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359368902.711, "dur": 3.209, + "args": { + "External id": 4724242,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359368904.795, "dur": 0.308, + "args": { + "External id": 4724243,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359368969.016, "dur": 88.838, + "args": { + "External id": 4724244,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359369078.449, "dur": 6.787, + "args": { + "External id": 4724245,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369081.972, "dur": 1.480, + "args": { + "External id": 4724246,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369086.669, "dur": 29.161, + "args": { + "External id": 4724247,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359369123.792, "dur": 6.236, + "args": { + "External id": 4724248,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359369125.580, "dur": 3.789, + "args": { + "External id": 4724249,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369127.346, "dur": 1.782, + "args": { + "External id": 4724250,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359369133.216, "dur": 53.405, + "args": { + "External id": 4724251,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359369134.186, "dur": 51.856, + "args": { + "External id": 4724252,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369190.568, "dur": 16.407, + "args": { + "External id": 4724253,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359369212.748, "dur": 5.694, + "args": { + "External id": 4724254,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369216.583, "dur": 1.065, + "args": { + "External id": 4724255,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359369222.718, "dur": 52.439, + "args": { + "External id": 4724256,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359369223.559, "dur": 4.245, + "args": { + "External id": 4724257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359369224.440, "dur": 2.796, + "args": { + "External id": 4724258,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369225.964, "dur": 1.121, + "args": { + "External id": 4724259,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359369228.406, "dur": 46.362, + "args": { + "External id": 4724260,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359369231.864, "dur": 42.364, + "args": { + "External id": 4724261,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359369278.774, "dur": 4.133, + "args": { + "External id": 4724262,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369280.689, "dur": 1.122, + "args": { + "External id": 4724263,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359369288.913, "dur": 1.515, + "args": { + "External id": 4724264,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359369297.623, "dur": 9.609, + "args": { + "External id": 4724265,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359369302.165, "dur": 4.798, + "args": { + "External id": 4724266,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359369387.687, "dur": 199.995, + "args": { + "External id": 4724267,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359369392.486, "dur": 2.410, + "args": { + "External id": 4724268,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359369396.134, "dur": 191.199, + "args": { + "External id": 4724269,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359369397.763, "dur": 0.594, + "args": { + "External id": 4724270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359369399.656, "dur": 21.963, + "args": { + "External id": 4724271,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359369423.080, "dur": 6.014, + "args": { + "External id": 4724272,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369427.476, "dur": 1.308, + "args": { + "External id": 4724273,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359369430.113, "dur": 30.181, + "args": { + "External id": 4724274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359369439.345, "dur": 1.442, + "args": { + "External id": 4724275,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359369442.245, "dur": 17.776, + "args": { + "External id": 4724276,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369444.702, "dur": 2.529, + "args": { + "External id": 4724277,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359369461.752, "dur": 21.462, + "args": { + "External id": 4724278,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369484.316, "dur": 15.770, + "args": { + "External id": 4724279,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359369502.999, "dur": 15.616, + "args": { + "External id": 4724280,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369519.806, "dur": 13.301, + "args": { + "External id": 4724281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359369535.082, "dur": 22.562, + "args": { + "External id": 4724282,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369536.643, "dur": 1.751, + "args": { + "External id": 4724283,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369542.618, "dur": 0.755, + "args": { + "External id": 4724284,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369558.915, "dur": 15.038, + "args": { + "External id": 4724285,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369575.103, "dur": 11.214, + "args": { + "External id": 4724286,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359369593.499, "dur": 1.297, + "args": { + "External id": 4724287,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359369603.235, "dur": 3.056, + "args": { + "External id": 4724288,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369605.373, "dur": 0.286, + "args": { + "External id": 4724289,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359369662.737, "dur": 45.184, + "args": { + "External id": 4724290,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359369711.990, "dur": 5.993, + "args": { + "External id": 4724291,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369716.281, "dur": 0.707, + "args": { + "External id": 4724292,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369718.916, "dur": 24.105, + "args": { + "External id": 4724293,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359369747.038, "dur": 4.898, + "args": { + "External id": 4724294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359369748.087, "dur": 3.201, + "args": { + "External id": 4724295,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369749.889, "dur": 1.238, + "args": { + "External id": 4724296,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359369754.222, "dur": 39.530, + "args": { + "External id": 4724297,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359369757.140, "dur": 36.022, + "args": { + "External id": 4724298,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369797.101, "dur": 14.714, + "args": { + "External id": 4724299,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359369815.800, "dur": 26.676, + "args": { + "External id": 4724300,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359369817.726, "dur": 24.376, + "args": { + "External id": 4724301,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369822.778, "dur": 2.341, + "args": { + "External id": 4724302,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359369847.280, "dur": 28.556, + "args": { + "External id": 4724303,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359369849.204, "dur": 26.454, + "args": { + "External id": 4724304,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 9959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359369853.578, "dur": 4.419, + "args": { + "External id": 4724305,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369861.197, "dur": 13.938, + "args": { + "External id": 4724306,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359369887.651, "dur": 5.084, + "args": { + "External id": 4724307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359369889.953, "dur": 2.555, + "args": { + "External id": 4724308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359369893.843, "dur": 1.247, + "args": { + "External id": 4724309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359369894.360, "dur": 0.637, + "args": { + "External id": 4724310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369934.437, "dur": 23.220, + "args": { + "External id": 4724311,"Sequence number": 47018984, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359369959.557, "dur": 15.646, + "args": { + "External id": 4724312,"Sequence number": 47018985, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9967 + } + }, + { + "ph": "s", "id": 9, "pid": 1336753, "tid": 1336753, "ts": 1712359369959.557, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359369980.520, "dur": 45.731, + "args": { + "External id": 4724313,"Sequence number": 47018986, "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": [[16, 4, 4096], [], [], [], []], "Ev Idx": 9968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370022.630, "dur": 1.446, + "args": { + "External id": 4724314,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1712359370043.599, "dur": 8.440, + "args": { + "External id": 4724315,"Sequence number": 47018986, "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": [[16, 4, 4096], [], []], "Ev Idx": 9970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370049.630, "dur": 1.076, + "args": { + "External id": 4724316,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359370053.865, "dur": 3.045, + "args": { + "External id": 4724317,"Sequence number": 47018986, "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": [[16, 4096], [], [], [], []], "Ev Idx": 9972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370055.566, "dur": 0.774, + "args": { + "External id": 4724318,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 9973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359370078.814, "dur": 7.803, + "args": { + "External id": 4724319,"Sequence number": 47018986, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9974 + } + }, + { + "ph": "s", "id": 8, "pid": 1336753, "tid": 1336753, "ts": 1712359370078.814, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370083.251, "dur": 1.380, + "args": { + "External id": 4724320,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359370088.112, "dur": 5.198, + "args": { + "External id": 4724321,"Sequence number": 47018987, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9976 + } + }, + { + "ph": "s", "id": 7, "pid": 1336753, "tid": 1336753, "ts": 1712359370088.112, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370091.767, "dur": 0.783, + "args": { + "External id": 4724322,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1712359370094.438, "dur": 7.472, + "args": { + "External id": 4724323,"Sequence number": 47018988, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 9978 + } + }, + { + "ph": "s", "id": 6, "pid": 1336753, "tid": 1336753, "ts": 1712359370094.438, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370100.400, "dur": 0.680, + "args": { + "External id": 4724324,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "6144"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359370102.814, "dur": 6.598, + "args": { + "External id": 4724325,"Sequence number": 47018989, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 9980 + } + }, + { + "ph": "s", "id": 5, "pid": 1336753, "tid": 1336753, "ts": 1712359370102.814, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370105.616, "dur": 2.995, + "args": { + "External id": 4724326,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "6144"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 9981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1712359370114.157, "dur": 37.259, + "args": { + "External id": 4724327,"Sequence number": 47018990, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712359370116.115, "dur": 35.054, + "args": { + "External id": 4724328,"Sequence number": 47018990, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359370119.176, "dur": 7.079, + "args": { + "External id": 4724329,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 9984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359370121.299, "dur": 4.390, + "args": { + "External id": 4724330,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359370127.223, "dur": 23.464, + "args": { + "External id": 4724331,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 9986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359370178.066, "dur": 5.545, + "args": { + "External id": 4724332,"Sequence number": 47018990, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 9987 + } + }, + { + "ph": "s", "id": 4, "pid": 1336753, "tid": 1336753, "ts": 1712359370178.066, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359370185.926, "dur": 1.367, + "args": { + "External id": 4724333,"Sequence number": 47018991, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336753, "tid": 1336753, + "ts": 1712359370218.786, "dur": 43917.843, + "args": { + "External id": 4724334,"Sequence number": 47018991, "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": [[8192, 1], [1], [2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536], [32000, 2048], [], [], [], [], []], "Ev Idx": 9989 + } + }, + { + "ph": "s", "id": 3, "pid": 1336753, "tid": 1336753, "ts": 1712359370218.786, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1712359370233.261, "dur": 27.272, + "args": { + "External id": 4724335,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712359370233.844, "dur": 26.487, + "args": { + "External id": 4724336,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359370234.835, "dur": 7.470, + "args": { + "External id": 4724337,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359370236.197, "dur": 5.539, + "args": { + "External id": 4724338,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359370242.882, "dur": 16.822, + "args": { + "External id": 4724339,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [8192, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 9994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359370275.040, "dur": 28.390, + "args": { + "External id": 4724340,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359370276.246, "dur": 9.081, + "args": { + "External id": 4724341,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370280.486, "dur": 4.340, + "args": { + "External id": 4724342,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359370286.779, "dur": 16.429, + "args": { + "External id": 4724343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359370288.863, "dur": 13.938, + "args": { + "External id": 4724344,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359370306.774, "dur": 19.310, + "args": { + "External id": 4724345,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 10000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359370307.968, "dur": 4.718, + "args": { + "External id": 4724346,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 10001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370309.628, "dur": 2.820, + "args": { + "External id": 4724347,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359370313.558, "dur": 12.341, + "args": { + "External id": 4724348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359370314.005, "dur": 11.542, + "args": { + "External id": 4724349,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 10004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1712359370331.257, "dur": 19.660, + "args": { + "External id": 4724350,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 10005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359370335.707, "dur": 3.148, + "args": { + "External id": 4724351,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712359370339.478, "dur": 11.180, + "args": { + "External id": 4724352,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 10007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359370340.095, "dur": 10.232, + "args": { + "External id": 4724353,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1712359370355.057, "dur": 22.720, + "args": { + "External id": 4724354,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359370380.372, "dur": 51.997, + "args": { + "External id": 4724355,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359370382.374, "dur": 49.511, + "args": { + "External id": 4724356,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370389.337, "dur": 0.825, + "args": { + "External id": 4724357,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359370391.929, "dur": 22.568, + "args": { + "External id": 4724358,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359370393.328, "dur": 20.937, + "args": { + "External id": 4724359,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 10014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359370395.835, "dur": 3.311, + "args": { + "External id": 4724360,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359370400.035, "dur": 13.726, + "args": { + "External id": 4724361,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 10016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1712359370438.441, "dur": 38031.036, + "args": { + "External id": 4724362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 10017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1712359370439.987, "dur": 38027.254, + "args": { + "External id": 4724363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 10018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359408483.444, "dur": 7.563, + "args": { + "External id": 4724364,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359408488.267, "dur": 1.087, + "args": { + "External id": 4724365,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359408496.159, "dur": 106.302, + "args": { + "External id": 4724366,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359408497.757, "dur": 8.224, + "args": { + "External id": 4724367,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359408500.380, "dur": 4.827, + "args": { + "External id": 4724368,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359408504.003, "dur": 0.958, + "args": { + "External id": 4724369,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359408507.572, "dur": 94.286, + "args": { + "External id": 4724370,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359408509.200, "dur": 91.864, + "args": { + "External id": 4724371,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359408605.514, "dur": 3.919, + "args": { + "External id": 4724372,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359408607.466, "dur": 0.990, + "args": { + "External id": 4724373,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359408616.340, "dur": 2.561, + "args": { + "External id": 4724374,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359408629.057, "dur": 6.431, + "args": { + "External id": 4724375,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359408631.333, "dur": 3.905, + "args": { + "External id": 4724376,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359408764.313, "dur": 213.047, + "args": { + "External id": 4724377,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359408768.888, "dur": 2.782, + "args": { + "External id": 4724378,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359408773.115, "dur": 203.705, + "args": { + "External id": 4724379,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359408774.710, "dur": 0.439, + "args": { + "External id": 4724380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359408776.615, "dur": 26.114, + "args": { + "External id": 4724381,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359408807.168, "dur": 5.442, + "args": { + "External id": 4724382,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359408811.567, "dur": 0.763, + "args": { + "External id": 4724383,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359408813.929, "dur": 23.863, + "args": { + "External id": 4724384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359408814.879, "dur": 1.635, + "args": { + "External id": 4724385,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359408817.622, "dur": 19.807, + "args": { + "External id": 4724386,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359408821.289, "dur": 3.226, + "args": { + "External id": 4724387,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359408839.444, "dur": 23.723, + "args": { + "External id": 4724388,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359408865.026, "dur": 17.657, + "args": { + "External id": 4724389,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359408886.358, "dur": 17.336, + "args": { + "External id": 4724390,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359408905.258, "dur": 13.384, + "args": { + "External id": 4724391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359408922.943, "dur": 23.817, + "args": { + "External id": 4724392,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359408924.991, "dur": 1.956, + "args": { + "External id": 4724393,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359408929.878, "dur": 0.822, + "args": { + "External id": 4724394,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359408948.164, "dur": 13.138, + "args": { + "External id": 4724395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359408962.969, "dur": 12.733, + "args": { + "External id": 4724396,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359409014.775, "dur": 2.578, + "args": { + "External id": 4724397,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359409027.652, "dur": 4.181, + "args": { + "External id": 4724398,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409030.159, "dur": 0.950, + "args": { + "External id": 4724399,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359409123.649, "dur": 71.420, + "args": { + "External id": 4724400,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359409200.302, "dur": 6.312, + "args": { + "External id": 4724401,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409203.090, "dur": 0.893, + "args": { + "External id": 4724402,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409208.138, "dur": 30.901, + "args": { + "External id": 4724403,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359409244.722, "dur": 9.517, + "args": { + "External id": 4724404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359409246.672, "dur": 6.764, + "args": { + "External id": 4724405,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409251.661, "dur": 1.529, + "args": { + "External id": 4724406,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359409257.448, "dur": 44.666, + "args": { + "External id": 4724407,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359409258.831, "dur": 42.673, + "args": { + "External id": 4724408,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409306.376, "dur": 17.148, + "args": { + "External id": 4724409,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359409329.384, "dur": 3.792, + "args": { + "External id": 4724410,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409331.291, "dur": 0.814, + "args": { + "External id": 4724411,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359409339.682, "dur": 48.169, + "args": { + "External id": 4724412,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359409340.560, "dur": 3.664, + "args": { + "External id": 4724413,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359409341.157, "dur": 2.496, + "args": { + "External id": 4724414,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409342.651, "dur": 0.860, + "args": { + "External id": 4724415,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359409344.826, "dur": 42.579, + "args": { + "External id": 4724416,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359409345.703, "dur": 41.098, + "args": { + "External id": 4724417,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359409393.708, "dur": 3.573, + "args": { + "External id": 4724418,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409395.639, "dur": 0.553, + "args": { + "External id": 4724419,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359409403.018, "dur": 1.546, + "args": { + "External id": 4724420,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359409412.120, "dur": 8.140, + "args": { + "External id": 4724421,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359409414.265, "dur": 5.696, + "args": { + "External id": 4724422,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359409514.112, "dur": 193.972, + "args": { + "External id": 4724423,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359409516.139, "dur": 1.995, + "args": { + "External id": 4724424,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359409519.411, "dur": 188.188, + "args": { + "External id": 4724425,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359409520.785, "dur": 0.302, + "args": { + "External id": 4724426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359409522.213, "dur": 25.229, + "args": { + "External id": 4724427,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359409548.864, "dur": 3.486, + "args": { + "External id": 4724428,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409551.118, "dur": 0.996, + "args": { + "External id": 4724429,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359409553.292, "dur": 27.754, + "args": { + "External id": 4724430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359409554.350, "dur": 1.669, + "args": { + "External id": 4724431,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359409557.296, "dur": 23.417, + "args": { + "External id": 4724432,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409564.875, "dur": 2.864, + "args": { + "External id": 4724433,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359409582.632, "dur": 21.130, + "args": { + "External id": 4724434,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409605.174, "dur": 15.109, + "args": { + "External id": 4724435,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359409623.111, "dur": 14.941, + "args": { + "External id": 4724436,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409639.553, "dur": 13.661, + "args": { + "External id": 4724437,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359409655.435, "dur": 21.205, + "args": { + "External id": 4724438,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409656.807, "dur": 1.897, + "args": { + "External id": 4724439,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409661.144, "dur": 1.022, + "args": { + "External id": 4724440,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409680.531, "dur": 13.352, + "args": { + "External id": 4724441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409695.158, "dur": 11.314, + "args": { + "External id": 4724442,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359409713.705, "dur": 1.714, + "args": { + "External id": 4724443,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359409723.473, "dur": 3.487, + "args": { + "External id": 4724444,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409725.788, "dur": 0.438, + "args": { + "External id": 4724445,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359409792.898, "dur": 46.971, + "args": { + "External id": 4724446,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359409844.278, "dur": 4.125, + "args": { + "External id": 4724447,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409846.278, "dur": 1.216, + "args": { + "External id": 4724448,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409852.090, "dur": 24.142, + "args": { + "External id": 4724449,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359409880.293, "dur": 4.937, + "args": { + "External id": 4724450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359409881.669, "dur": 2.955, + "args": { + "External id": 4724451,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409883.512, "dur": 0.913, + "args": { + "External id": 4724452,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359409887.453, "dur": 40.266, + "args": { + "External id": 4724453,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359409888.505, "dur": 38.552, + "args": { + "External id": 4724454,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359409931.303, "dur": 14.817, + "args": { + "External id": 4724455,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359409952.960, "dur": 3.142, + "args": { + "External id": 4724456,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409954.680, "dur": 0.737, + "args": { + "External id": 4724457,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359409959.489, "dur": 91.780, + "args": { + "External id": 4724458,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359409960.470, "dur": 5.930, + "args": { + "External id": 4724459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359409961.339, "dur": 4.493, + "args": { + "External id": 4724460,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359409963.157, "dur": 2.488, + "args": { + "External id": 4724461,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359409969.458, "dur": 81.028, + "args": { + "External id": 4724462,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359409969.985, "dur": 79.383, + "args": { + "External id": 4724463,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359410057.395, "dur": 4.710, + "args": { + "External id": 4724464,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410059.848, "dur": 0.931, + "args": { + "External id": 4724465,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359410082.916, "dur": 2.044, + "args": { + "External id": 4724466,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359410092.768, "dur": 7.316, + "args": { + "External id": 4724467,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359410094.826, "dur": 4.989, + "args": { + "External id": 4724468,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359410188.879, "dur": 195.854, + "args": { + "External id": 4724469,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359410191.501, "dur": 2.060, + "args": { + "External id": 4724470,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359410194.814, "dur": 189.339, + "args": { + "External id": 4724471,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359410196.209, "dur": 0.303, + "args": { + "External id": 4724472,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359410200.379, "dur": 26.149, + "args": { + "External id": 4724473,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359410228.019, "dur": 3.714, + "args": { + "External id": 4724474,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410230.654, "dur": 0.818, + "args": { + "External id": 4724475,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359410232.653, "dur": 26.478, + "args": { + "External id": 4724476,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359410233.678, "dur": 3.445, + "args": { + "External id": 4724477,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359410238.640, "dur": 20.236, + "args": { + "External id": 4724478,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410243.648, "dur": 2.466, + "args": { + "External id": 4724479,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359410260.718, "dur": 20.764, + "args": { + "External id": 4724480,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410282.699, "dur": 14.290, + "args": { + "External id": 4724481,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359410299.836, "dur": 15.057, + "args": { + "External id": 4724482,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410316.347, "dur": 13.234, + "args": { + "External id": 4724483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359410331.282, "dur": 21.670, + "args": { + "External id": 4724484,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410332.811, "dur": 1.689, + "args": { + "External id": 4724485,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410336.961, "dur": 0.886, + "args": { + "External id": 4724486,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410356.588, "dur": 13.198, + "args": { + "External id": 4724487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410370.989, "dur": 12.196, + "args": { + "External id": 4724488,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359410390.433, "dur": 1.512, + "args": { + "External id": 4724489,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359410399.907, "dur": 3.846, + "args": { + "External id": 4724490,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410402.591, "dur": 0.364, + "args": { + "External id": 4724491,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359410465.839, "dur": 81.471, + "args": { + "External id": 4724492,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359410551.925, "dur": 6.389, + "args": { + "External id": 4724493,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410556.250, "dur": 1.170, + "args": { + "External id": 4724494,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410559.928, "dur": 29.090, + "args": { + "External id": 4724495,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359410593.209, "dur": 7.433, + "args": { + "External id": 4724496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359410594.663, "dur": 5.268, + "args": { + "External id": 4724497,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410596.519, "dur": 3.182, + "args": { + "External id": 4724498,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359410603.494, "dur": 72.042, + "args": { + "External id": 4724499,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359410604.772, "dur": 70.154, + "args": { + "External id": 4724500,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410681.190, "dur": 22.941, + "args": { + "External id": 4724501,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359410709.305, "dur": 3.287, + "args": { + "External id": 4724502,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410711.392, "dur": 0.465, + "args": { + "External id": 4724503,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359410716.483, "dur": 56.209, + "args": { + "External id": 4724504,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359410717.757, "dur": 6.174, + "args": { + "External id": 4724505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359410718.588, "dur": 4.680, + "args": { + "External id": 4724506,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410722.290, "dur": 0.821, + "args": { + "External id": 4724507,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359410724.751, "dur": 47.547, + "args": { + "External id": 4724508,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359410725.939, "dur": 45.787, + "args": { + "External id": 4724509,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359410776.265, "dur": 15.362, + "args": { + "External id": 4724510,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410789.899, "dur": 0.664, + "args": { + "External id": 4724511,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359410796.756, "dur": 1.301, + "args": { + "External id": 4724512,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359410806.899, "dur": 7.244, + "args": { + "External id": 4724513,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359410808.588, "dur": 5.342, + "args": { + "External id": 4724514,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359410890.279, "dur": 243.042, + "args": { + "External id": 4724515,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359410892.773, "dur": 2.795, + "args": { + "External id": 4724516,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359410896.706, "dur": 235.759, + "args": { + "External id": 4724517,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359410898.216, "dur": 0.194, + "args": { + "External id": 4724518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359410899.630, "dur": 22.568, + "args": { + "External id": 4724519,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359410926.115, "dur": 3.096, + "args": { + "External id": 4724520,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359410928.277, "dur": 0.728, + "args": { + "External id": 4724521,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359410930.598, "dur": 23.407, + "args": { + "External id": 4724522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359410931.435, "dur": 2.043, + "args": { + "External id": 4724523,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359410935.095, "dur": 18.541, + "args": { + "External id": 4724524,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410939.265, "dur": 2.156, + "args": { + "External id": 4724525,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359410955.347, "dur": 18.922, + "args": { + "External id": 4724526,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359410975.522, "dur": 51.938, + "args": { + "External id": 4724527,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359411031.593, "dur": 16.299, + "args": { + "External id": 4724528,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411049.399, "dur": 12.492, + "args": { + "External id": 4724529,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359411079.049, "dur": 25.603, + "args": { + "External id": 4724530,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411081.473, "dur": 2.637, + "args": { + "External id": 4724531,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411086.612, "dur": 0.954, + "args": { + "External id": 4724532,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411106.213, "dur": 13.117, + "args": { + "External id": 4724533,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411120.444, "dur": 10.882, + "args": { + "External id": 4724534,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359411140.805, "dur": 2.483, + "args": { + "External id": 4724535,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359411152.482, "dur": 3.805, + "args": { + "External id": 4724536,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411155.056, "dur": 0.408, + "args": { + "External id": 4724537,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359411226.993, "dur": 54.416, + "args": { + "External id": 4724538,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359411285.935, "dur": 4.409, + "args": { + "External id": 4724539,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411288.067, "dur": 1.244, + "args": { + "External id": 4724540,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411291.510, "dur": 24.715, + "args": { + "External id": 4724541,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359411320.740, "dur": 7.709, + "args": { + "External id": 4724542,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359411322.081, "dur": 5.417, + "args": { + "External id": 4724543,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411326.467, "dur": 0.855, + "args": { + "External id": 4724544,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359411331.202, "dur": 40.627, + "args": { + "External id": 4724545,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359411332.392, "dur": 38.859, + "args": { + "External id": 4724546,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411375.191, "dur": 15.503, + "args": { + "External id": 4724547,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359411395.638, "dur": 3.678, + "args": { + "External id": 4724548,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411397.395, "dur": 1.191, + "args": { + "External id": 4724549,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359411402.901, "dur": 50.750, + "args": { + "External id": 4724550,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359411406.200, "dur": 5.323, + "args": { + "External id": 4724551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359411406.881, "dur": 4.034, + "args": { + "External id": 4724552,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411408.444, "dur": 2.312, + "args": { + "External id": 4724553,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359411412.420, "dur": 40.830, + "args": { + "External id": 4724554,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359411413.082, "dur": 39.477, + "args": { + "External id": 4724555,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359411457.148, "dur": 3.358, + "args": { + "External id": 4724556,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411458.760, "dur": 0.656, + "args": { + "External id": 4724557,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359411465.366, "dur": 1.307, + "args": { + "External id": 4724558,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359411475.664, "dur": 5.960, + "args": { + "External id": 4724559,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359411477.495, "dur": 3.869, + "args": { + "External id": 4724560,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359411560.472, "dur": 189.499, + "args": { + "External id": 4724561,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359411562.714, "dur": 2.032, + "args": { + "External id": 4724562,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359411566.006, "dur": 183.530, + "args": { + "External id": 4724563,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359411567.354, "dur": 0.336, + "args": { + "External id": 4724564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359411573.387, "dur": 21.119, + "args": { + "External id": 4724565,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359411600.439, "dur": 3.658, + "args": { + "External id": 4724566,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411602.861, "dur": 0.924, + "args": { + "External id": 4724567,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359411605.002, "dur": 23.609, + "args": { + "External id": 4724568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359411605.787, "dur": 3.553, + "args": { + "External id": 4724569,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359411610.571, "dur": 17.749, + "args": { + "External id": 4724570,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411613.368, "dur": 2.222, + "args": { + "External id": 4724571,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359411629.790, "dur": 20.411, + "args": { + "External id": 4724572,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411651.335, "dur": 13.439, + "args": { + "External id": 4724573,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359411667.022, "dur": 14.035, + "args": { + "External id": 4724574,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411684.447, "dur": 13.326, + "args": { + "External id": 4724575,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359411699.398, "dur": 19.443, + "args": { + "External id": 4724576,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411700.659, "dur": 1.598, + "args": { + "External id": 4724577,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411704.352, "dur": 0.485, + "args": { + "External id": 4724578,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411720.105, "dur": 13.399, + "args": { + "External id": 4724579,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411734.558, "dur": 11.688, + "args": { + "External id": 4724580,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359411755.414, "dur": 1.510, + "args": { + "External id": 4724581,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359411763.666, "dur": 3.397, + "args": { + "External id": 4724582,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411765.777, "dur": 0.539, + "args": { + "External id": 4724583,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359411825.891, "dur": 45.263, + "args": { + "External id": 4724584,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359411875.389, "dur": 3.747, + "args": { + "External id": 4724585,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411877.543, "dur": 0.725, + "args": { + "External id": 4724586,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411880.337, "dur": 25.040, + "args": { + "External id": 4724587,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359411909.605, "dur": 9.701, + "args": { + "External id": 4724588,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359411913.008, "dur": 5.717, + "args": { + "External id": 4724589,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359411915.465, "dur": 3.056, + "args": { + "External id": 4724590,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359411921.628, "dur": 37.908, + "args": { + "External id": 4724591,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359411922.630, "dur": 36.261, + "args": { + "External id": 4724592,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359411962.979, "dur": 15.007, + "args": { + "External id": 4724593,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359411982.647, "dur": 44.037, + "args": { + "External id": 4724594,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412024.048, "dur": 1.116, + "args": { + "External id": 4724595,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359412031.819, "dur": 68.534, + "args": { + "External id": 4724596,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359412032.701, "dur": 4.699, + "args": { + "External id": 4724597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359412033.834, "dur": 3.056, + "args": { + "External id": 4724598,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412035.654, "dur": 1.077, + "args": { + "External id": 4724599,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359412038.135, "dur": 61.764, + "args": { + "External id": 4724600,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359412039.105, "dur": 59.853, + "args": { + "External id": 4724601,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359412107.986, "dur": 4.528, + "args": { + "External id": 4724602,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412110.157, "dur": 0.871, + "args": { + "External id": 4724603,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359412118.731, "dur": 1.527, + "args": { + "External id": 4724604,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359412127.626, "dur": 7.431, + "args": { + "External id": 4724605,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359412129.505, "dur": 5.339, + "args": { + "External id": 4724606,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359412220.287, "dur": 193.048, + "args": { + "External id": 4724607,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359412222.635, "dur": 2.418, + "args": { + "External id": 4724608,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359412228.174, "dur": 184.704, + "args": { + "External id": 4724609,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359412229.473, "dur": 0.345, + "args": { + "External id": 4724610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359412230.881, "dur": 26.507, + "args": { + "External id": 4724611,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359412258.732, "dur": 5.962, + "args": { + "External id": 4724612,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412261.225, "dur": 3.218, + "args": { + "External id": 4724613,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359412265.697, "dur": 24.762, + "args": { + "External id": 4724614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359412266.536, "dur": 1.692, + "args": { + "External id": 4724615,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359412271.688, "dur": 18.370, + "args": { + "External id": 4724616,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412274.551, "dur": 2.553, + "args": { + "External id": 4724617,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359412291.906, "dur": 21.169, + "args": { + "External id": 4724618,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412314.827, "dur": 14.199, + "args": { + "External id": 4724619,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359412331.784, "dur": 14.451, + "args": { + "External id": 4724620,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412347.631, "dur": 12.874, + "args": { + "External id": 4724621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359412362.072, "dur": 23.062, + "args": { + "External id": 4724622,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412364.188, "dur": 1.741, + "args": { + "External id": 4724623,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412370.018, "dur": 1.185, + "args": { + "External id": 4724624,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412386.444, "dur": 13.031, + "args": { + "External id": 4724625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412400.894, "dur": 10.911, + "args": { + "External id": 4724626,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359412419.468, "dur": 1.468, + "args": { + "External id": 4724627,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359412428.658, "dur": 3.793, + "args": { + "External id": 4724628,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412430.897, "dur": 0.551, + "args": { + "External id": 4724629,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359412492.545, "dur": 49.469, + "args": { + "External id": 4724630,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359412546.577, "dur": 7.943, + "args": { + "External id": 4724631,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412551.139, "dur": 2.472, + "args": { + "External id": 4724632,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412555.689, "dur": 25.049, + "args": { + "External id": 4724633,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359412584.508, "dur": 5.146, + "args": { + "External id": 4724634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359412586.037, "dur": 2.994, + "args": { + "External id": 4724635,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412587.684, "dur": 1.175, + "args": { + "External id": 4724636,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359412592.285, "dur": 38.835, + "args": { + "External id": 4724637,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359412593.223, "dur": 37.337, + "args": { + "External id": 4724638,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412636.770, "dur": 14.829, + "args": { + "External id": 4724639,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359412656.258, "dur": 3.715, + "args": { + "External id": 4724640,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412658.383, "dur": 0.861, + "args": { + "External id": 4724641,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359412663.491, "dur": 46.893, + "args": { + "External id": 4724642,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359412664.512, "dur": 5.534, + "args": { + "External id": 4724643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359412665.285, "dur": 4.260, + "args": { + "External id": 4724644,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412668.513, "dur": 0.927, + "args": { + "External id": 4724645,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359412670.519, "dur": 39.540, + "args": { + "External id": 4724646,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359412671.465, "dur": 38.078, + "args": { + "External id": 4724647,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359412713.664, "dur": 3.676, + "args": { + "External id": 4724648,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412715.536, "dur": 0.801, + "args": { + "External id": 4724649,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359412721.956, "dur": 1.086, + "args": { + "External id": 4724650,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359412729.198, "dur": 7.846, + "args": { + "External id": 4724651,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359412732.662, "dur": 4.139, + "args": { + "External id": 4724652,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359412807.321, "dur": 176.349, + "args": { + "External id": 4724653,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359412809.099, "dur": 4.044, + "args": { + "External id": 4724654,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359412814.397, "dur": 168.526, + "args": { + "External id": 4724655,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359412815.542, "dur": 0.269, + "args": { + "External id": 4724656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359412816.799, "dur": 18.840, + "args": { + "External id": 4724657,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359412836.934, "dur": 5.476, + "args": { + "External id": 4724658,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412841.163, "dur": 0.932, + "args": { + "External id": 4724659,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359412843.351, "dur": 22.610, + "args": { + "External id": 4724660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359412844.859, "dur": 1.627, + "args": { + "External id": 4724661,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359412849.957, "dur": 15.696, + "args": { + "External id": 4724662,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412851.873, "dur": 2.137, + "args": { + "External id": 4724663,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359412867.086, "dur": 19.400, + "args": { + "External id": 4724664,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412887.769, "dur": 12.622, + "args": { + "External id": 4724665,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359412902.627, "dur": 14.247, + "args": { + "External id": 4724666,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412918.076, "dur": 12.844, + "args": { + "External id": 4724667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359412932.202, "dur": 24.389, + "args": { + "External id": 4724668,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412936.186, "dur": 1.762, + "args": { + "External id": 4724669,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359412941.928, "dur": 0.937, + "args": { + "External id": 4724670,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412957.818, "dur": 12.077, + "args": { + "External id": 4724671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359412970.690, "dur": 11.273, + "args": { + "External id": 4724672,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359413028.147, "dur": 2.238, + "args": { + "External id": 4724673,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359413039.897, "dur": 3.393, + "args": { + "External id": 4724674,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413041.856, "dur": 0.691, + "args": { + "External id": 4724675,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359413124.196, "dur": 53.999, + "args": { + "External id": 4724676,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359413183.048, "dur": 7.859, + "args": { + "External id": 4724677,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413188.198, "dur": 1.301, + "args": { + "External id": 4724678,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413192.044, "dur": 25.716, + "args": { + "External id": 4724679,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359413222.741, "dur": 6.137, + "args": { + "External id": 4724680,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359413224.564, "dur": 3.715, + "args": { + "External id": 4724681,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413226.341, "dur": 1.734, + "args": { + "External id": 4724682,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359413231.627, "dur": 40.652, + "args": { + "External id": 4724683,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359413234.797, "dur": 36.907, + "args": { + "External id": 4724684,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413275.657, "dur": 16.017, + "args": { + "External id": 4724685,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359413296.696, "dur": 4.207, + "args": { + "External id": 4724686,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413298.889, "dur": 1.227, + "args": { + "External id": 4724687,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1712359413304.382, "dur": 49.290, + "args": { + "External id": 4724688,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359413305.328, "dur": 5.690, + "args": { + "External id": 4724689,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359413305.909, "dur": 4.600, + "args": { + "External id": 4724690,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413309.488, "dur": 0.825, + "args": { + "External id": 4724691,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359413311.810, "dur": 41.490, + "args": { + "External id": 4724692,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359413312.305, "dur": 40.529, + "args": { + "External id": 4724693,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359413356.956, "dur": 4.181, + "args": { + "External id": 4724694,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413358.946, "dur": 1.001, + "args": { + "External id": 4724695,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359413366.127, "dur": 1.549, + "args": { + "External id": 4724696,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359413376.550, "dur": 6.553, + "args": { + "External id": 4724697,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359413378.218, "dur": 4.627, + "args": { + "External id": 4724698,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359413455.292, "dur": 187.033, + "args": { + "External id": 4724699,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359413460.034, "dur": 3.007, + "args": { + "External id": 4724700,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1712359413464.794, "dur": 176.883, + "args": { + "External id": 4724701,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1712359413466.446, "dur": 0.346, + "args": { + "External id": 4724702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1712359413470.590, "dur": 20.785, + "args": { + "External id": 4724703,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1712359413493.079, "dur": 5.135, + "args": { + "External id": 4724704,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413497.124, "dur": 0.738, + "args": { + "External id": 4724705,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359413498.976, "dur": 21.414, + "args": { + "External id": 4724706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712359413500.016, "dur": 1.435, + "args": { + "External id": 4724707,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712359413502.490, "dur": 17.572, + "args": { + "External id": 4724708,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413504.761, "dur": 2.420, + "args": { + "External id": 4724709,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712359413521.588, "dur": 19.650, + "args": { + "External id": 4724710,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413542.426, "dur": 15.975, + "args": { + "External id": 4724711,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1712359413560.758, "dur": 14.242, + "args": { + "External id": 4724712,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413578.750, "dur": 12.615, + "args": { + "External id": 4724713,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359413592.949, "dur": 22.136, + "args": { + "External id": 4724714,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413594.654, "dur": 1.721, + "args": { + "External id": 4724715,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413599.352, "dur": 0.959, + "args": { + "External id": 4724716,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413616.324, "dur": 12.713, + "args": { + "External id": 4724717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413630.073, "dur": 10.597, + "args": { + "External id": 4724718,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712359413649.520, "dur": 1.636, + "args": { + "External id": 4724719,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359413658.349, "dur": 2.936, + "args": { + "External id": 4724720,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413660.221, "dur": 0.268, + "args": { + "External id": 4724721,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359413718.349, "dur": 42.858, + "args": { + "External id": 4724722,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1712359413765.151, "dur": 4.073, + "args": { + "External id": 4724723,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413767.113, "dur": 1.280, + "args": { + "External id": 4724724,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413770.456, "dur": 22.004, + "args": { + "External id": 4724725,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1712359413796.565, "dur": 7.310, + "args": { + "External id": 4724726,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1712359413797.676, "dur": 5.635, + "args": { + "External id": 4724727,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413801.586, "dur": 1.567, + "args": { + "External id": 4724728,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1712359413805.923, "dur": 39.293, + "args": { + "External id": 4724729,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1712359413806.882, "dur": 37.851, + "args": { + "External id": 4724730,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359413848.533, "dur": 15.123, + "args": { + "External id": 4724731,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359413868.081, "dur": 25.912, + "args": { + "External id": 4724732,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1712359413870.095, "dur": 23.512, + "args": { + "External id": 4724733,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359413875.785, "dur": 3.239, + "args": { + "External id": 4724734,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712359413898.754, "dur": 189.208, + "args": { + "External id": 4724735,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 10390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1712359413900.765, "dur": 186.827, + "args": { + "External id": 4724736,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 10391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359414043.151, "dur": 6.708, + "args": { + "External id": 4724737,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712359414052.207, "dur": 34.274, + "args": { + "External id": 4724738,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359414105.096, "dur": 4.900, + "args": { + "External id": 4724739,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 10394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359414106.756, "dur": 2.962, + "args": { + "External id": 4724740,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 10395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359414111.231, "dur": 1.076, + "args": { + "External id": 4724741,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1712359414111.793, "dur": 0.436, + "args": { + "External id": 4724742,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359414153.765, "dur": 29.692, + "args": { + "External id": 4724743,"Sequence number": 47018992, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 10398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1712359414185.298, "dur": 15.028, + "args": { + "External id": 4724744,"Sequence number": 47018993, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 10399 + } + }, + { + "ph": "s", "id": 2, "pid": 1336753, "tid": 1336753, "ts": 1712359414185.298, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 1336753, "tid": 1336753, + "ts": 1712359414313.555, "dur": 40.420, + "args": { + "External id": 4724745,"Record function id": 0, "Ev Idx": 10400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1336753, + "ts": 1712359414456.716, "dur": 35.087, + "args": { + "External id": 4724746,"Sequence number": 47018994, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 10401 + } + }, + { + "ph": "s", "id": 1, "pid": 1336753, "tid": 1336753, "ts": 1712359414456.716, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359414553.888, "dur": 28.094, + "args": { + "External id": 4724747,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 10402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712359414555.499, "dur": 8.841, + "args": { + "External id": 4724748,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 10403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712359414559.419, "dur": 4.354, + "args": { + "External id": 4724749,"Record function id": 0, "Concrete Inputs": ["[1]", "[1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712359414565.860, "dur": 15.825, + "args": { + "External id": 4724750,"Record function id": 0, "Concrete Inputs": ["", "1."], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 10405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1336753, + "ts": 1712360740550.802, "dur": 62.302, + "args": { + "External id": 4724751,"Sequence number": 47018995, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1336753, + "ts": 1712360740622.484, "dur": 22.761, + "args": { + "External id": 4724752,"Sequence number": 47018996, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 10407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1712360740653.498, "dur": 23.161, + "args": { + "External id": 4724753,"Sequence number": 47018997, "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": 10408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1712360741360.422, "dur": 32.574, + "args": { + "External id": 4724754,"Sequence number": 47018998, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 10409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1712360742076.260, "dur": 34.461, + "args": { + "External id": 4724755,"Sequence number": 47018999, "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": 10410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 1336753, "tid": 1336753, + "ts": 1712360743943.491, "dur": 3404.272, + "args": { + "External id": 4724756,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 10411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 1336753, "tid": 1336753, + "ts": 1712360744674.792, "dur": 1091.622, + "args": { + "External id": 4724757,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 10412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1712360744694.011, "dur": 63.692, + "args": { + "External id": 4724758,"Record function id": 0, "Concrete Inputs": ["[36375]", "6", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 10413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712360744697.266, "dur": 12.120, + "args": { + "External id": 4724759,"Record function id": 0, "Concrete Inputs": ["[36375]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1712360744711.846, "dur": 45.562, + "args": { + "External id": 4724760,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[36375]], "Ev Idx": 10415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1712360744714.065, "dur": 42.863, + "args": { + "External id": 4724761,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[36375], []], "Ev Idx": 10416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747383.086, "dur": 3.207, + "args": { + "External id": 4724762,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747388.321, "dur": 0.497, + "args": { + "External id": 4724763,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747389.972, "dur": 0.471, + "args": { + "External id": 4724764,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747391.427, "dur": 0.232, + "args": { + "External id": 4724765,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747392.831, "dur": 0.387, + "args": { + "External id": 4724766,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747394.196, "dur": 0.322, + "args": { + "External id": 4724767,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747395.694, "dur": 0.321, + "args": { + "External id": 4724768,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747399.538, "dur": 0.418, + "args": { + "External id": 4724769,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747400.952, "dur": 0.450, + "args": { + "External id": 4724770,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747402.320, "dur": 0.626, + "args": { + "External id": 4724771,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747403.940, "dur": 0.411, + "args": { + "External id": 4724772,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747405.464, "dur": 0.235, + "args": { + "External id": 4724773,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747406.617, "dur": 0.309, + "args": { + "External id": 4724774,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747407.742, "dur": 0.221, + "args": { + "External id": 4724775,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747409.032, "dur": 0.208, + "args": { + "External id": 4724776,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747412.171, "dur": 0.211, + "args": { + "External id": 4724777,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747413.096, "dur": 0.207, + "args": { + "External id": 4724778,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747414.323, "dur": 0.210, + "args": { + "External id": 4724779,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747415.468, "dur": 0.206, + "args": { + "External id": 4724780,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747416.529, "dur": 0.246, + "args": { + "External id": 4724781,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747417.619, "dur": 0.317, + "args": { + "External id": 4724782,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747418.854, "dur": 0.333, + "args": { + "External id": 4724783,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747420.096, "dur": 0.416, + "args": { + "External id": 4724784,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747423.652, "dur": 0.415, + "args": { + "External id": 4724785,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747425.088, "dur": 0.448, + "args": { + "External id": 4724786,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747426.444, "dur": 0.412, + "args": { + "External id": 4724787,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747427.764, "dur": 0.479, + "args": { + "External id": 4724788,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747429.056, "dur": 0.238, + "args": { + "External id": 4724789,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747430.387, "dur": 0.432, + "args": { + "External id": 4724790,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747431.529, "dur": 0.331, + "args": { + "External id": 4724791,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747432.685, "dur": 0.207, + "args": { + "External id": 4724792,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747436.409, "dur": 0.217, + "args": { + "External id": 4724793,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747437.475, "dur": 0.206, + "args": { + "External id": 4724794,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747438.742, "dur": 0.220, + "args": { + "External id": 4724795,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747439.702, "dur": 0.209, + "args": { + "External id": 4724796,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747440.889, "dur": 0.217, + "args": { + "External id": 4724797,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747442.000, "dur": 0.255, + "args": { + "External id": 4724798,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747443.001, "dur": 0.208, + "args": { + "External id": 4724799,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747444.142, "dur": 0.213, + "args": { + "External id": 4724800,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747447.467, "dur": 0.217, + "args": { + "External id": 4724801,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747448.552, "dur": 0.216, + "args": { + "External id": 4724802,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747449.684, "dur": 0.210, + "args": { + "External id": 4724803,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747450.917, "dur": 0.210, + "args": { + "External id": 4724804,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747451.852, "dur": 0.216, + "args": { + "External id": 4724805,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747452.865, "dur": 0.203, + "args": { + "External id": 4724806,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747455.680, "dur": 0.220, + "args": { + "External id": 4724807,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747456.644, "dur": 0.203, + "args": { + "External id": 4724808,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747459.902, "dur": 0.213, + "args": { + "External id": 4724809,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747460.846, "dur": 0.203, + "args": { + "External id": 4724810,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747461.766, "dur": 0.207, + "args": { + "External id": 4724811,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747462.700, "dur": 0.199, + "args": { + "External id": 4724812,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747463.672, "dur": 0.207, + "args": { + "External id": 4724813,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747464.584, "dur": 0.202, + "args": { + "External id": 4724814,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747465.748, "dur": 0.210, + "args": { + "External id": 4724815,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747466.660, "dur": 0.204, + "args": { + "External id": 4724816,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747470.015, "dur": 0.210, + "args": { + "External id": 4724817,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747470.937, "dur": 0.202, + "args": { + "External id": 4724818,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747471.840, "dur": 0.207, + "args": { + "External id": 4724819,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747472.751, "dur": 0.437, + "args": { + "External id": 4724820,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747473.883, "dur": 0.204, + "args": { + "External id": 4724821,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747474.795, "dur": 0.412, + "args": { + "External id": 4724822,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747475.924, "dur": 0.403, + "args": { + "External id": 4724823,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747477.188, "dur": 0.446, + "args": { + "External id": 4724824,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747480.622, "dur": 0.571, + "args": { + "External id": 4724825,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747482.112, "dur": 0.343, + "args": { + "External id": 4724826,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747483.289, "dur": 0.349, + "args": { + "External id": 4724827,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747484.429, "dur": 0.339, + "args": { + "External id": 4724828,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747485.466, "dur": 0.204, + "args": { + "External id": 4724829,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747486.401, "dur": 0.337, + "args": { + "External id": 4724830,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747487.549, "dur": 0.316, + "args": { + "External id": 4724831,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747489.005, "dur": 0.345, + "args": { + "External id": 4724832,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747492.094, "dur": 0.352, + "args": { + "External id": 4724833,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747493.313, "dur": 0.368, + "args": { + "External id": 4724834,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747494.388, "dur": 0.207, + "args": { + "External id": 4724835,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747495.459, "dur": 0.199, + "args": { + "External id": 4724836,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747496.344, "dur": 0.204, + "args": { + "External id": 4724837,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747497.255, "dur": 0.198, + "args": { + "External id": 4724838,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747498.833, "dur": 0.900, + "args": { + "External id": 4724839,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747500.464, "dur": 0.525, + "args": { + "External id": 4724840,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747504.123, "dur": 0.412, + "args": { + "External id": 4724841,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747505.395, "dur": 0.479, + "args": { + "External id": 4724842,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747506.642, "dur": 0.425, + "args": { + "External id": 4724843,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747507.838, "dur": 0.421, + "args": { + "External id": 4724844,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747509.006, "dur": 0.207, + "args": { + "External id": 4724845,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747509.959, "dur": 0.470, + "args": { + "External id": 4724846,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747511.188, "dur": 0.385, + "args": { + "External id": 4724847,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747512.524, "dur": 0.210, + "args": { + "External id": 4724848,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747515.805, "dur": 0.208, + "args": { + "External id": 4724849,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747516.738, "dur": 0.224, + "args": { + "External id": 4724850,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747517.691, "dur": 0.244, + "args": { + "External id": 4724851,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747518.738, "dur": 0.203, + "args": { + "External id": 4724852,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747519.659, "dur": 0.206, + "args": { + "External id": 4724853,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747520.566, "dur": 0.200, + "args": { + "External id": 4724854,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747522.317, "dur": 0.209, + "args": { + "External id": 4724855,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747523.268, "dur": 0.200, + "args": { + "External id": 4724856,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747526.456, "dur": 0.207, + "args": { + "External id": 4724857,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747527.522, "dur": 0.213, + "args": { + "External id": 4724858,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747528.467, "dur": 0.250, + "args": { + "External id": 4724859,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747529.435, "dur": 0.227, + "args": { + "External id": 4724860,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747530.402, "dur": 0.206, + "args": { + "External id": 4724861,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747531.363, "dur": 0.203, + "args": { + "External id": 4724862,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747532.305, "dur": 0.206, + "args": { + "External id": 4724863,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747533.414, "dur": 0.201, + "args": { + "External id": 4724864,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747536.392, "dur": 0.205, + "args": { + "External id": 4724865,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747537.544, "dur": 0.200, + "args": { + "External id": 4724866,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747538.464, "dur": 0.227, + "args": { + "External id": 4724867,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747539.577, "dur": 0.410, + "args": { + "External id": 4724868,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747540.713, "dur": 0.204, + "args": { + "External id": 4724869,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747541.676, "dur": 0.394, + "args": { + "External id": 4724870,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747543.257, "dur": 0.387, + "args": { + "External id": 4724871,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747544.605, "dur": 0.219, + "args": { + "External id": 4724872,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747548.273, "dur": 0.255, + "args": { + "External id": 4724873,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747549.294, "dur": 0.364, + "args": { + "External id": 4724874,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747550.570, "dur": 0.416, + "args": { + "External id": 4724875,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747551.868, "dur": 0.237, + "args": { + "External id": 4724876,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747552.952, "dur": 0.206, + "args": { + "External id": 4724877,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747554.135, "dur": 0.202, + "args": { + "External id": 4724878,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747555.159, "dur": 0.213, + "args": { + "External id": 4724879,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747556.063, "dur": 0.209, + "args": { + "External id": 4724880,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747558.938, "dur": 0.205, + "args": { + "External id": 4724881,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747559.915, "dur": 0.242, + "args": { + "External id": 4724882,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747560.922, "dur": 0.206, + "args": { + "External id": 4724883,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747561.836, "dur": 0.206, + "args": { + "External id": 4724884,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747562.757, "dur": 0.204, + "args": { + "External id": 4724885,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747563.659, "dur": 0.202, + "args": { + "External id": 4724886,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747564.555, "dur": 0.407, + "args": { + "External id": 4724887,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747565.700, "dur": 0.203, + "args": { + "External id": 4724888,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747568.686, "dur": 0.417, + "args": { + "External id": 4724889,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747570.019, "dur": 0.525, + "args": { + "External id": 4724890,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747571.753, "dur": 0.437, + "args": { + "External id": 4724891,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747572.924, "dur": 0.407, + "args": { + "External id": 4724892,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747574.037, "dur": 0.203, + "args": { + "External id": 4724893,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747575.165, "dur": 0.174, + "args": { + "External id": 4724894,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747576.068, "dur": 0.414, + "args": { + "External id": 4724895,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747577.180, "dur": 0.335, + "args": { + "External id": 4724896,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747580.537, "dur": 0.402, + "args": { + "External id": 4724897,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747581.634, "dur": 1.019, + "args": { + "External id": 4724898,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747583.365, "dur": 0.428, + "args": { + "External id": 4724899,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747584.535, "dur": 0.389, + "args": { + "External id": 4724900,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747585.640, "dur": 0.203, + "args": { + "External id": 4724901,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747586.547, "dur": 0.201, + "args": { + "External id": 4724902,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747587.459, "dur": 0.422, + "args": { + "External id": 4724903,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747588.648, "dur": 0.400, + "args": { + "External id": 4724904,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747591.861, "dur": 0.425, + "args": { + "External id": 4724905,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747593.019, "dur": 0.460, + "args": { + "External id": 4724906,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747594.171, "dur": 0.208, + "args": { + "External id": 4724907,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747595.129, "dur": 0.224, + "args": { + "External id": 4724908,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747596.050, "dur": 0.222, + "args": { + "External id": 4724909,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747596.995, "dur": 0.198, + "args": { + "External id": 4724910,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747598.397, "dur": 0.207, + "args": { + "External id": 4724911,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747599.524, "dur": 0.566, + "args": { + "External id": 4724912,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747603.033, "dur": 0.354, + "args": { + "External id": 4724913,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747604.302, "dur": 0.243, + "args": { + "External id": 4724914,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747605.239, "dur": 0.310, + "args": { + "External id": 4724915,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747606.465, "dur": 0.354, + "args": { + "External id": 4724916,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747607.534, "dur": 0.207, + "args": { + "External id": 4724917,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747608.626, "dur": 0.322, + "args": { + "External id": 4724918,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747609.670, "dur": 0.207, + "args": { + "External id": 4724919,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747610.747, "dur": 0.202, + "args": { + "External id": 4724920,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747615.533, "dur": 0.244, + "args": { + "External id": 4724921,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747616.691, "dur": 0.222, + "args": { + "External id": 4724922,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747617.868, "dur": 0.241, + "args": { + "External id": 4724923,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747618.847, "dur": 0.202, + "args": { + "External id": 4724924,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747619.770, "dur": 0.210, + "args": { + "External id": 4724925,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747620.699, "dur": 0.203, + "args": { + "External id": 4724926,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747621.610, "dur": 0.204, + "args": { + "External id": 4724927,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747622.526, "dur": 0.200, + "args": { + "External id": 4724928,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747625.691, "dur": 0.209, + "args": { + "External id": 4724929,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747626.600, "dur": 0.206, + "args": { + "External id": 4724930,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747627.497, "dur": 0.202, + "args": { + "External id": 4724931,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747628.403, "dur": 0.203, + "args": { + "External id": 4724932,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747629.326, "dur": 0.207, + "args": { + "External id": 4724933,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747630.257, "dur": 0.202, + "args": { + "External id": 4724934,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747631.617, "dur": 0.215, + "args": { + "External id": 4724935,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747632.541, "dur": 0.210, + "args": { + "External id": 4724936,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747635.903, "dur": 0.234, + "args": { + "External id": 4724937,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747636.917, "dur": 0.210, + "args": { + "External id": 4724938,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747637.839, "dur": 0.208, + "args": { + "External id": 4724939,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747638.857, "dur": 0.208, + "args": { + "External id": 4724940,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747639.885, "dur": 0.208, + "args": { + "External id": 4724941,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747640.806, "dur": 0.201, + "args": { + "External id": 4724942,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747641.881, "dur": 0.211, + "args": { + "External id": 4724943,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747642.817, "dur": 0.442, + "args": { + "External id": 4724944,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747646.236, "dur": 0.447, + "args": { + "External id": 4724945,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747647.383, "dur": 0.325, + "args": { + "External id": 4724946,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747648.414, "dur": 0.336, + "args": { + "External id": 4724947,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747649.451, "dur": 0.339, + "args": { + "External id": 4724948,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747650.484, "dur": 0.207, + "args": { + "External id": 4724949,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747651.414, "dur": 0.311, + "args": { + "External id": 4724950,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747652.414, "dur": 0.342, + "args": { + "External id": 4724951,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747653.462, "dur": 0.341, + "args": { + "External id": 4724952,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747656.610, "dur": 0.325, + "args": { + "External id": 4724953,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747657.812, "dur": 0.343, + "args": { + "External id": 4724954,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747658.865, "dur": 0.360, + "args": { + "External id": 4724955,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747660.109, "dur": 0.202, + "args": { + "External id": 4724956,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747660.995, "dur": 0.237, + "args": { + "External id": 4724957,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747662.092, "dur": 0.201, + "args": { + "External id": 4724958,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747662.983, "dur": 0.204, + "args": { + "External id": 4724959,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747664.142, "dur": 0.206, + "args": { + "External id": 4724960,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747667.061, "dur": 0.226, + "args": { + "External id": 4724961,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747668.124, "dur": 0.222, + "args": { + "External id": 4724962,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747669.550, "dur": 0.229, + "args": { + "External id": 4724963,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747670.559, "dur": 0.207, + "args": { + "External id": 4724964,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747671.445, "dur": 0.209, + "args": { + "External id": 4724965,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747672.371, "dur": 0.203, + "args": { + "External id": 4724966,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747673.301, "dur": 0.209, + "args": { + "External id": 4724967,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747674.244, "dur": 0.200, + "args": { + "External id": 4724968,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747677.201, "dur": 0.213, + "args": { + "External id": 4724969,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747678.123, "dur": 0.200, + "args": { + "External id": 4724970,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747679.043, "dur": 0.648, + "args": { + "External id": 4724971,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747680.403, "dur": 0.334, + "args": { + "External id": 4724972,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747681.428, "dur": 0.208, + "args": { + "External id": 4724973,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747682.341, "dur": 0.360, + "args": { + "External id": 4724974,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747683.421, "dur": 0.207, + "args": { + "External id": 4724975,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747684.404, "dur": 0.203, + "args": { + "External id": 4724976,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747687.771, "dur": 0.208, + "args": { + "External id": 4724977,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747688.733, "dur": 0.201, + "args": { + "External id": 4724978,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747689.652, "dur": 0.211, + "args": { + "External id": 4724979,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747690.663, "dur": 0.211, + "args": { + "External id": 4724980,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747691.603, "dur": 0.240, + "args": { + "External id": 4724981,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747692.614, "dur": 0.202, + "args": { + "External id": 4724982,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747693.557, "dur": 0.208, + "args": { + "External id": 4724983,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747694.506, "dur": 0.228, + "args": { + "External id": 4724984,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747698.044, "dur": 0.725, + "args": { + "External id": 4724985,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747699.477, "dur": 0.329, + "args": { + "External id": 4724986,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747700.502, "dur": 0.214, + "args": { + "External id": 4724987,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747701.496, "dur": 0.357, + "args": { + "External id": 4724988,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747702.543, "dur": 0.206, + "args": { + "External id": 4724989,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747703.623, "dur": 0.206, + "args": { + "External id": 4724990,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747704.709, "dur": 0.175, + "args": { + "External id": 4724991,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747705.599, "dur": 0.336, + "args": { + "External id": 4724992,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747708.628, "dur": 0.354, + "args": { + "External id": 4724993,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747709.730, "dur": 0.231, + "args": { + "External id": 4724994,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747711.089, "dur": 0.228, + "args": { + "External id": 4724995,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747712.065, "dur": 0.221, + "args": { + "External id": 4724996,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747713.076, "dur": 0.211, + "args": { + "External id": 4724997,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747714.039, "dur": 0.203, + "args": { + "External id": 4724998,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747714.958, "dur": 0.208, + "args": { + "External id": 4724999,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747715.872, "dur": 0.203, + "args": { + "External id": 4725000,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747719.089, "dur": 0.214, + "args": { + "External id": 4725001,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747720.112, "dur": 0.202, + "args": { + "External id": 4725002,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747721.274, "dur": 0.205, + "args": { + "External id": 4725003,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747722.180, "dur": 0.199, + "args": { + "External id": 4725004,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747723.079, "dur": 0.210, + "args": { + "External id": 4725005,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747724.114, "dur": 0.220, + "args": { + "External id": 4725006,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747725.087, "dur": 0.210, + "args": { + "External id": 4725007,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747726.227, "dur": 0.227, + "args": { + "External id": 4725008,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747729.551, "dur": 0.236, + "args": { + "External id": 4725009,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747730.504, "dur": 0.202, + "args": { + "External id": 4725010,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747731.444, "dur": 0.205, + "args": { + "External id": 4725011,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747732.342, "dur": 0.200, + "args": { + "External id": 4725012,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747733.336, "dur": 0.232, + "args": { + "External id": 4725013,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747734.281, "dur": 0.201, + "args": { + "External id": 4725014,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747735.274, "dur": 0.231, + "args": { + "External id": 4725015,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747736.204, "dur": 0.200, + "args": { + "External id": 4725016,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747739.258, "dur": 0.207, + "args": { + "External id": 4725017,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747742.064, "dur": 0.203, + "args": { + "External id": 4725018,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747743.287, "dur": 0.213, + "args": { + "External id": 4725019,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747744.220, "dur": 0.232, + "args": { + "External id": 4725020,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747745.198, "dur": 0.209, + "args": { + "External id": 4725021,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747746.158, "dur": 0.239, + "args": { + "External id": 4725022,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747747.121, "dur": 0.206, + "args": { + "External id": 4725023,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747748.042, "dur": 0.205, + "args": { + "External id": 4725024,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747751.040, "dur": 0.206, + "args": { + "External id": 4725025,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747751.955, "dur": 0.369, + "args": { + "External id": 4725026,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747753.092, "dur": 0.211, + "args": { + "External id": 4725027,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747754.007, "dur": 0.318, + "args": { + "External id": 4725028,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747755.078, "dur": 0.204, + "args": { + "External id": 4725029,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747756.006, "dur": 0.375, + "args": { + "External id": 4725030,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747757.466, "dur": 0.346, + "args": { + "External id": 4725031,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747758.509, "dur": 0.311, + "args": { + "External id": 4725032,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747762.426, "dur": 0.225, + "args": { + "External id": 4725033,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747763.427, "dur": 0.364, + "args": { + "External id": 4725034,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747766.292, "dur": 0.241, + "args": { + "External id": 4725035,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747767.252, "dur": 0.200, + "args": { + "External id": 4725036,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747768.142, "dur": 0.205, + "args": { + "External id": 4725037,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747769.071, "dur": 0.198, + "args": { + "External id": 4725038,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747769.992, "dur": 0.206, + "args": { + "External id": 4725039,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747771.077, "dur": 0.197, + "args": { + "External id": 4725040,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747774.370, "dur": 0.211, + "args": { + "External id": 4725041,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747775.412, "dur": 0.321, + "args": { + "External id": 4725042,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747776.478, "dur": 0.327, + "args": { + "External id": 4725043,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747777.532, "dur": 0.474, + "args": { + "External id": 4725044,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747778.729, "dur": 0.205, + "args": { + "External id": 4725045,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747779.623, "dur": 0.206, + "args": { + "External id": 4725046,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747780.518, "dur": 0.207, + "args": { + "External id": 4725047,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747781.412, "dur": 0.201, + "args": { + "External id": 4725048,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747784.751, "dur": 0.211, + "args": { + "External id": 4725049,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747785.733, "dur": 0.201, + "args": { + "External id": 4725050,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747786.648, "dur": 0.226, + "args": { + "External id": 4725051,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360747787.573, "dur": 0.220, + "args": { + "External id": 4725052,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336753, "tid": 1336753, + "ts": 1712360747842.824, "dur": 1800.043, + "args": { + "External id": 4725053,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336753, "tid": 1336753, + "ts": 1712360748350.417, "dur": 1212.008, + "args": { + "External id": 4725054,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748359.567, "dur": 7.313, + "args": { + "External id": 4725055,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748363.151, "dur": 3.176, + "args": { + "External id": 4725056,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748367.571, "dur": 3.551, + "args": { + "External id": 4725057,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748368.251, "dur": 2.711, + "args": { + "External id": 4725058,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748371.550, "dur": 3.391, + "args": { + "External id": 4725059,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748374.208, "dur": 0.643, + "args": { + "External id": 4725060,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748375.409, "dur": 2.080, + "args": { + "External id": 4725061,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748375.918, "dur": 1.306, + "args": { + "External id": 4725062,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748379.889, "dur": 5.287, + "args": { + "External id": 4725063,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748384.645, "dur": 0.463, + "args": { + "External id": 4725064,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748385.471, "dur": 1.474, + "args": { + "External id": 4725065,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748386.176, "dur": 0.706, + "args": { + "External id": 4725066,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748387.296, "dur": 2.104, + "args": { + "External id": 4725067,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748387.925, "dur": 1.215, + "args": { + "External id": 4725068,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748389.626, "dur": 3.272, + "args": { + "External id": 4725069,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748392.261, "dur": 0.572, + "args": { + "External id": 4725070,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748393.122, "dur": 1.379, + "args": { + "External id": 4725071,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748393.678, "dur": 0.760, + "args": { + "External id": 4725072,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748394.756, "dur": 3.548, + "args": { + "External id": 4725073,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748395.410, "dur": 2.782, + "args": { + "External id": 4725074,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748398.564, "dur": 3.148, + "args": { + "External id": 4725075,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748401.044, "dur": 0.603, + "args": { + "External id": 4725076,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748401.937, "dur": 1.289, + "args": { + "External id": 4725077,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748402.307, "dur": 0.849, + "args": { + "External id": 4725078,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748405.433, "dur": 5.479, + "args": { + "External id": 4725079,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748410.242, "dur": 0.600, + "args": { + "External id": 4725080,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748411.152, "dur": 1.648, + "args": { + "External id": 4725081,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748411.665, "dur": 1.067, + "args": { + "External id": 4725082,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748413.029, "dur": 1.649, + "args": { + "External id": 4725083,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748413.504, "dur": 0.892, + "args": { + "External id": 4725084,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748414.922, "dur": 3.918, + "args": { + "External id": 4725085,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748417.736, "dur": 0.826, + "args": { + "External id": 4725086,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748419.070, "dur": 1.980, + "args": { + "External id": 4725087,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748419.990, "dur": 0.990, + "args": { + "External id": 4725088,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748421.396, "dur": 3.101, + "args": { + "External id": 4725089,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748421.918, "dur": 2.506, + "args": { + "External id": 4725090,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748424.746, "dur": 4.602, + "args": { + "External id": 4725091,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748428.093, "dur": 0.980, + "args": { + "External id": 4725092,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748429.593, "dur": 1.646, + "args": { + "External id": 4725093,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748430.065, "dur": 1.104, + "args": { + "External id": 4725094,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748433.731, "dur": 4.961, + "args": { + "External id": 4725095,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748437.968, "dur": 0.658, + "args": { + "External id": 4725096,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748438.951, "dur": 1.502, + "args": { + "External id": 4725097,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748439.473, "dur": 0.915, + "args": { + "External id": 4725098,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748440.700, "dur": 1.549, + "args": { + "External id": 4725099,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748441.356, "dur": 0.822, + "args": { + "External id": 4725100,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748442.472, "dur": 3.860, + "args": { + "External id": 4725101,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748445.355, "dur": 0.910, + "args": { + "External id": 4725102,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748446.562, "dur": 1.432, + "args": { + "External id": 4725103,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748447.200, "dur": 0.729, + "args": { + "External id": 4725104,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748448.216, "dur": 3.176, + "args": { + "External id": 4725105,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748448.719, "dur": 2.598, + "args": { + "External id": 4725106,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748451.638, "dur": 2.976, + "args": { + "External id": 4725107,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748453.631, "dur": 0.915, + "args": { + "External id": 4725108,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748454.838, "dur": 1.476, + "args": { + "External id": 4725109,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748455.205, "dur": 0.783, + "args": { + "External id": 4725110,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748458.630, "dur": 5.194, + "args": { + "External id": 4725111,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748463.049, "dur": 0.710, + "args": { + "External id": 4725112,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748464.080, "dur": 1.456, + "args": { + "External id": 4725113,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748464.605, "dur": 0.868, + "args": { + "External id": 4725114,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748465.843, "dur": 1.538, + "args": { + "External id": 4725115,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748466.501, "dur": 0.807, + "args": { + "External id": 4725116,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748467.604, "dur": 3.988, + "args": { + "External id": 4725117,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748470.473, "dur": 1.055, + "args": { + "External id": 4725118,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748471.817, "dur": 1.453, + "args": { + "External id": 4725119,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748472.452, "dur": 0.752, + "args": { + "External id": 4725120,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748473.504, "dur": 3.199, + "args": { + "External id": 4725121,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748474.242, "dur": 2.291, + "args": { + "External id": 4725122,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748476.928, "dur": 5.421, + "args": { + "External id": 4725123,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748481.320, "dur": 0.962, + "args": { + "External id": 4725124,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748482.595, "dur": 2.563, + "args": { + "External id": 4725125,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748482.975, "dur": 2.109, + "args": { + "External id": 4725126,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748487.663, "dur": 2.486, + "args": { + "External id": 4725127,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748489.327, "dur": 0.758, + "args": { + "External id": 4725128,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748490.382, "dur": 1.667, + "args": { + "External id": 4725129,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748491.102, "dur": 0.878, + "args": { + "External id": 4725130,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748492.329, "dur": 3.923, + "args": { + "External id": 4725131,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748495.386, "dur": 0.795, + "args": { + "External id": 4725132,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748496.496, "dur": 3.261, + "args": { + "External id": 4725133,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748498.541, "dur": 1.151, + "args": { + "External id": 4725134,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748499.983, "dur": 1.492, + "args": { + "External id": 4725135,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748500.511, "dur": 0.892, + "args": { + "External id": 4725136,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748501.702, "dur": 3.168, + "args": { + "External id": 4725137,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748504.036, "dur": 0.771, + "args": { + "External id": 4725138,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748505.097, "dur": 2.627, + "args": { + "External id": 4725139,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748506.898, "dur": 0.564, + "args": { + "External id": 4725140,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748507.942, "dur": 2.802, + "args": { + "External id": 4725141,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748508.309, "dur": 2.178, + "args": { + "External id": 4725142,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748513.395, "dur": 2.693, + "args": { + "External id": 4725143,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748515.264, "dur": 0.759, + "args": { + "External id": 4725144,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748516.342, "dur": 1.550, + "args": { + "External id": 4725145,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748516.837, "dur": 0.985, + "args": { + "External id": 4725146,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748518.135, "dur": 3.853, + "args": { + "External id": 4725147,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748521.216, "dur": 0.709, + "args": { + "External id": 4725148,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748522.243, "dur": 2.218, + "args": { + "External id": 4725149,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748523.844, "dur": 0.552, + "args": { + "External id": 4725150,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748524.688, "dur": 1.107, + "args": { + "External id": 4725151,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748525.050, "dur": 0.675, + "args": { + "External id": 4725152,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748526.021, "dur": 3.256, + "args": { + "External id": 4725153,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748528.457, "dur": 0.754, + "args": { + "External id": 4725154,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748529.500, "dur": 2.337, + "args": { + "External id": 4725155,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748530.752, "dur": 0.796, + "args": { + "External id": 4725156,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748532.086, "dur": 3.587, + "args": { + "External id": 4725157,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748532.971, "dur": 2.457, + "args": { + "External id": 4725158,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748537.974, "dur": 2.132, + "args": { + "External id": 4725159,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748539.466, "dur": 0.569, + "args": { + "External id": 4725160,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748540.367, "dur": 1.850, + "args": { + "External id": 4725161,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748541.275, "dur": 0.872, + "args": { + "External id": 4725162,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748542.462, "dur": 4.746, + "args": { + "External id": 4725163,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748545.862, "dur": 1.285, + "args": { + "External id": 4725164,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748547.536, "dur": 1.397, + "args": { + "External id": 4725165,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748548.281, "dur": 0.584, + "args": { + "External id": 4725166,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748549.157, "dur": 2.004, + "args": { + "External id": 4725167,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748550.044, "dur": 1.046, + "args": { + "External id": 4725168,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748551.410, "dur": 3.048, + "args": { + "External id": 4725169,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748553.771, "dur": 0.616, + "args": { + "External id": 4725170,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748554.680, "dur": 2.095, + "args": { + "External id": 4725171,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748555.980, "dur": 0.733, + "args": { + "External id": 4725172,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748557.041, "dur": 3.304, + "args": { + "External id": 4725173,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748557.817, "dur": 2.278, + "args": { + "External id": 4725174,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748562.582, "dur": 1.764, + "args": { + "External id": 4725175,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748563.506, "dur": 0.773, + "args": { + "External id": 4725176,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748564.624, "dur": 1.702, + "args": { + "External id": 4725177,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748565.383, "dur": 0.872, + "args": { + "External id": 4725178,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748566.554, "dur": 3.821, + "args": { + "External id": 4725179,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748569.603, "dur": 0.704, + "args": { + "External id": 4725180,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748570.659, "dur": 1.809, + "args": { + "External id": 4725181,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748571.639, "dur": 0.762, + "args": { + "External id": 4725182,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748572.713, "dur": 2.599, + "args": { + "External id": 4725183,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748574.063, "dur": 1.178, + "args": { + "External id": 4725184,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748575.572, "dur": 3.264, + "args": { + "External id": 4725185,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748578.150, "dur": 0.613, + "args": { + "External id": 4725186,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748579.061, "dur": 2.048, + "args": { + "External id": 4725187,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748580.195, "dur": 0.847, + "args": { + "External id": 4725188,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748581.361, "dur": 3.287, + "args": { + "External id": 4725189,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748582.237, "dur": 2.334, + "args": { + "External id": 4725190,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748586.961, "dur": 2.418, + "args": { + "External id": 4725191,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748588.200, "dur": 0.711, + "args": { + "External id": 4725192,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748589.634, "dur": 1.667, + "args": { + "External id": 4725193,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748590.377, "dur": 0.853, + "args": { + "External id": 4725194,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748591.530, "dur": 4.151, + "args": { + "External id": 4725195,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748594.695, "dur": 0.920, + "args": { + "External id": 4725196,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748596.044, "dur": 1.487, + "args": { + "External id": 4725197,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748596.678, "dur": 0.781, + "args": { + "External id": 4725198,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748597.758, "dur": 2.063, + "args": { + "External id": 4725199,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748598.966, "dur": 0.785, + "args": { + "External id": 4725200,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748600.082, "dur": 3.804, + "args": { + "External id": 4725201,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748602.876, "dur": 0.737, + "args": { + "External id": 4725202,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748604.233, "dur": 2.164, + "args": { + "External id": 4725203,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748605.534, "dur": 0.794, + "args": { + "External id": 4725204,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748606.647, "dur": 3.503, + "args": { + "External id": 4725205,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748607.606, "dur": 2.471, + "args": { + "External id": 4725206,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748612.534, "dur": 2.053, + "args": { + "External id": 4725207,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748613.662, "dur": 0.861, + "args": { + "External id": 4725208,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748615.064, "dur": 2.296, + "args": { + "External id": 4725209,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748616.259, "dur": 1.031, + "args": { + "External id": 4725210,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748617.724, "dur": 4.162, + "args": { + "External id": 4725211,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748620.905, "dur": 0.915, + "args": { + "External id": 4725212,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748622.161, "dur": 1.555, + "args": { + "External id": 4725213,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748622.836, "dur": 0.617, + "args": { + "External id": 4725214,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748623.939, "dur": 2.031, + "args": { + "External id": 4725215,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748625.197, "dur": 0.702, + "args": { + "External id": 4725216,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748626.256, "dur": 3.531, + "args": { + "External id": 4725217,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748629.072, "dur": 0.651, + "args": { + "External id": 4725218,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748630.150, "dur": 2.278, + "args": { + "External id": 4725219,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748631.627, "dur": 0.736, + "args": { + "External id": 4725220,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748632.700, "dur": 3.073, + "args": { + "External id": 4725221,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748633.583, "dur": 2.113, + "args": { + "External id": 4725222,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748638.041, "dur": 2.721, + "args": { + "External id": 4725223,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748639.757, "dur": 0.922, + "args": { + "External id": 4725224,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748641.221, "dur": 2.355, + "args": { + "External id": 4725225,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748642.208, "dur": 1.076, + "args": { + "External id": 4725226,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748643.877, "dur": 4.131, + "args": { + "External id": 4725227,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748647.022, "dur": 0.922, + "args": { + "External id": 4725228,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748648.278, "dur": 1.702, + "args": { + "External id": 4725229,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748649.118, "dur": 0.797, + "args": { + "External id": 4725230,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748650.204, "dur": 2.366, + "args": { + "External id": 4725231,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748651.391, "dur": 0.933, + "args": { + "External id": 4725232,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748652.823, "dur": 3.865, + "args": { + "External id": 4725233,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748655.568, "dur": 0.867, + "args": { + "External id": 4725234,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748656.921, "dur": 2.365, + "args": { + "External id": 4725235,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748657.955, "dur": 1.073, + "args": { + "External id": 4725236,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748659.553, "dur": 3.107, + "args": { + "External id": 4725237,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748660.412, "dur": 2.174, + "args": { + "External id": 4725238,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748664.997, "dur": 2.379, + "args": { + "External id": 4725239,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748666.320, "dur": 0.812, + "args": { + "External id": 4725240,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748667.674, "dur": 1.876, + "args": { + "External id": 4725241,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748668.791, "dur": 0.686, + "args": { + "External id": 4725242,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748669.781, "dur": 4.408, + "args": { + "External id": 4725243,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748673.232, "dur": 0.895, + "args": { + "External id": 4725244,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748674.514, "dur": 1.518, + "args": { + "External id": 4725245,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748675.227, "dur": 0.561, + "args": { + "External id": 4725246,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748676.263, "dur": 2.204, + "args": { + "External id": 4725247,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748677.379, "dur": 1.014, + "args": { + "External id": 4725248,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748752.637, "dur": 3.866, + "args": { + "External id": 4731393,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748755.646, "dur": 0.719, + "args": { + "External id": 4731394,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748756.878, "dur": 1.787, + "args": { + "External id": 4731395,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748757.830, "dur": 0.768, + "args": { + "External id": 4731396,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748758.956, "dur": 2.850, + "args": { + "External id": 4731397,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748759.654, "dur": 2.078, + "args": { + "External id": 4731398,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748764.645, "dur": 1.720, + "args": { + "External id": 4731399,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748765.694, "dur": 0.607, + "args": { + "External id": 4731400,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748766.684, "dur": 2.087, + "args": { + "External id": 4731401,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748767.743, "dur": 0.958, + "args": { + "External id": 4731402,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748769.027, "dur": 3.662, + "args": { + "External id": 4731403,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748771.929, "dur": 0.663, + "args": { + "External id": 4731404,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748772.969, "dur": 1.369, + "args": { + "External id": 4731405,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748773.649, "dur": 0.621, + "args": { + "External id": 4731406,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748774.581, "dur": 2.068, + "args": { + "External id": 4731407,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748775.718, "dur": 0.861, + "args": { + "External id": 4731408,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748776.911, "dur": 3.174, + "args": { + "External id": 4731409,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748779.397, "dur": 0.618, + "args": { + "External id": 4731410,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748780.325, "dur": 1.657, + "args": { + "External id": 4731411,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748781.345, "dur": 0.570, + "args": { + "External id": 4731412,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748782.342, "dur": 3.113, + "args": { + "External id": 4731413,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748783.016, "dur": 2.369, + "args": { + "External id": 4731414,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748788.080, "dur": 1.710, + "args": { + "External id": 4731415,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748789.142, "dur": 0.579, + "args": { + "External id": 4731416,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748790.367, "dur": 1.388, + "args": { + "External id": 4731417,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748790.986, "dur": 0.700, + "args": { + "External id": 4731418,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748792.215, "dur": 3.896, + "args": { + "External id": 4731419,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748795.633, "dur": 0.408, + "args": { + "External id": 4731420,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748796.389, "dur": 1.665, + "args": { + "External id": 4731421,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748797.250, "dur": 0.736, + "args": { + "External id": 4731422,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748798.337, "dur": 1.857, + "args": { + "External id": 4731423,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748799.449, "dur": 0.678, + "args": { + "External id": 4731424,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748800.432, "dur": 3.450, + "args": { + "External id": 4731425,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748802.817, "dur": 0.761, + "args": { + "External id": 4731426,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748804.190, "dur": 1.977, + "args": { + "External id": 4731427,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748805.221, "dur": 0.880, + "args": { + "External id": 4731428,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748806.463, "dur": 3.297, + "args": { + "External id": 4731429,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748807.098, "dur": 2.402, + "args": { + "External id": 4731430,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748812.127, "dur": 2.310, + "args": { + "External id": 4731431,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748813.600, "dur": 0.773, + "args": { + "External id": 4731432,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748814.889, "dur": 1.743, + "args": { + "External id": 4731433,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748815.719, "dur": 0.845, + "args": { + "External id": 4731434,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748816.854, "dur": 4.073, + "args": { + "External id": 4731435,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748820.100, "dur": 0.760, + "args": { + "External id": 4731436,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748821.198, "dur": 1.757, + "args": { + "External id": 4731437,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748821.891, "dur": 0.995, + "args": { + "External id": 4731438,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748823.362, "dur": 2.004, + "args": { + "External id": 4731439,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748824.573, "dur": 0.726, + "args": { + "External id": 4731440,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748825.686, "dur": 3.729, + "args": { + "External id": 4731441,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748828.766, "dur": 0.576, + "args": { + "External id": 4731442,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748829.833, "dur": 1.760, + "args": { + "External id": 4731443,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748830.724, "dur": 0.802, + "args": { + "External id": 4731444,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748832.163, "dur": 3.251, + "args": { + "External id": 4731445,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748833.026, "dur": 2.318, + "args": { + "External id": 4731446,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748837.833, "dur": 1.935, + "args": { + "External id": 4731447,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748838.926, "dur": 0.773, + "args": { + "External id": 4731448,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748840.219, "dur": 1.549, + "args": { + "External id": 4731449,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748840.871, "dur": 0.830, + "args": { + "External id": 4731450,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748841.991, "dur": 4.171, + "args": { + "External id": 4731451,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748845.322, "dur": 0.773, + "args": { + "External id": 4731452,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748846.425, "dur": 1.748, + "args": { + "External id": 4731453,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748847.304, "dur": 0.804, + "args": { + "External id": 4731454,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748848.420, "dur": 1.972, + "args": { + "External id": 4731455,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748849.346, "dur": 0.979, + "args": { + "External id": 4731456,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748850.698, "dur": 3.040, + "args": { + "External id": 4731457,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748853.062, "dur": 0.608, + "args": { + "External id": 4731458,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748854.190, "dur": 1.854, + "args": { + "External id": 4731459,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748855.442, "dur": 0.535, + "args": { + "External id": 4731460,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748856.392, "dur": 3.004, + "args": { + "External id": 4731461,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748857.046, "dur": 2.280, + "args": { + "External id": 4731462,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748861.899, "dur": 2.363, + "args": { + "External id": 4731463,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748863.378, "dur": 0.815, + "args": { + "External id": 4731464,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748864.751, "dur": 1.671, + "args": { + "External id": 4731465,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748865.644, "dur": 0.709, + "args": { + "External id": 4731466,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748866.644, "dur": 4.498, + "args": { + "External id": 4731467,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748870.468, "dur": 0.609, + "args": { + "External id": 4731468,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748871.407, "dur": 1.627, + "args": { + "External id": 4731469,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748872.227, "dur": 0.744, + "args": { + "External id": 4731470,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748873.502, "dur": 2.149, + "args": { + "External id": 4731471,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748874.716, "dur": 0.868, + "args": { + "External id": 4731472,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748875.931, "dur": 3.182, + "args": { + "External id": 4731473,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748878.290, "dur": 0.761, + "args": { + "External id": 4731474,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748879.336, "dur": 1.559, + "args": { + "External id": 4731475,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748880.242, "dur": 0.592, + "args": { + "External id": 4731476,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748881.338, "dur": 3.059, + "args": { + "External id": 4731477,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748882.275, "dur": 1.810, + "args": { + "External id": 4731478,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748887.525, "dur": 1.850, + "args": { + "External id": 4731479,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748888.524, "dur": 0.786, + "args": { + "External id": 4731480,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748889.708, "dur": 2.038, + "args": { + "External id": 4731481,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748890.786, "dur": 0.892, + "args": { + "External id": 4731482,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748891.970, "dur": 4.162, + "args": { + "External id": 4731483,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748895.309, "dur": 0.756, + "args": { + "External id": 4731484,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748896.419, "dur": 1.630, + "args": { + "External id": 4731485,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748897.237, "dur": 0.747, + "args": { + "External id": 4731486,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748898.296, "dur": 1.920, + "args": { + "External id": 4731487,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748899.456, "dur": 0.693, + "args": { + "External id": 4731488,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748900.456, "dur": 3.159, + "args": { + "External id": 4731489,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748902.929, "dur": 0.620, + "args": { + "External id": 4731490,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748903.861, "dur": 2.077, + "args": { + "External id": 4731491,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748905.089, "dur": 0.781, + "args": { + "External id": 4731492,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748906.244, "dur": 2.835, + "args": { + "External id": 4731493,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748906.944, "dur": 1.894, + "args": { + "External id": 4731494,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748911.592, "dur": 1.939, + "args": { + "External id": 4731495,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748912.727, "dur": 0.742, + "args": { + "External id": 4731496,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748913.974, "dur": 1.448, + "args": { + "External id": 4731497,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748914.773, "dur": 0.584, + "args": { + "External id": 4731498,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748915.646, "dur": 3.735, + "args": { + "External id": 4731499,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748918.723, "dur": 0.588, + "args": { + "External id": 4731500,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748919.761, "dur": 1.349, + "args": { + "External id": 4731501,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748920.474, "dur": 0.571, + "args": { + "External id": 4731502,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748921.368, "dur": 1.949, + "args": { + "External id": 4731503,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748922.375, "dur": 0.875, + "args": { + "External id": 4731504,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748923.792, "dur": 2.991, + "args": { + "External id": 4731505,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748926.081, "dur": 0.636, + "args": { + "External id": 4731506,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748927.008, "dur": 1.766, + "args": { + "External id": 4731507,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748928.070, "dur": 0.642, + "args": { + "External id": 4731508,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748929.128, "dur": 3.412, + "args": { + "External id": 4731509,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748930.092, "dur": 2.376, + "args": { + "External id": 4731510,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748935.363, "dur": 1.805, + "args": { + "External id": 4731511,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748936.341, "dur": 0.520, + "args": { + "External id": 4731512,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748937.408, "dur": 1.416, + "args": { + "External id": 4731513,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748938.101, "dur": 0.658, + "args": { + "External id": 4731514,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748939.096, "dur": 3.638, + "args": { + "External id": 4731515,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748941.885, "dur": 0.777, + "args": { + "External id": 4731516,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748943.090, "dur": 1.680, + "args": { + "External id": 4731517,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748943.974, "dur": 0.730, + "args": { + "External id": 4731518,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748945.349, "dur": 1.985, + "args": { + "External id": 4731519,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748946.567, "dur": 0.705, + "args": { + "External id": 4731520,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748947.589, "dur": 3.539, + "args": { + "External id": 4731521,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748950.232, "dur": 0.833, + "args": { + "External id": 4731522,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748951.466, "dur": 3.603, + "args": { + "External id": 4731523,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748954.357, "dur": 0.646, + "args": { + "External id": 4731524,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748955.336, "dur": 2.834, + "args": { + "External id": 4731525,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748956.006, "dur": 2.063, + "args": { + "External id": 4731526,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748960.450, "dur": 2.043, + "args": { + "External id": 4731527,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748961.756, "dur": 0.673, + "args": { + "External id": 4731528,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748962.947, "dur": 1.525, + "args": { + "External id": 4731529,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748963.680, "dur": 0.730, + "args": { + "External id": 4731530,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748964.704, "dur": 4.429, + "args": { + "External id": 4731531,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748968.201, "dur": 0.858, + "args": { + "External id": 4731532,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748969.395, "dur": 1.663, + "args": { + "External id": 4731533,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748970.340, "dur": 0.649, + "args": { + "External id": 4731534,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748971.279, "dur": 2.115, + "args": { + "External id": 4731535,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748972.448, "dur": 0.881, + "args": { + "External id": 4731536,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748973.839, "dur": 3.591, + "args": { + "External id": 4731537,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748976.619, "dur": 0.749, + "args": { + "External id": 4731538,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748977.844, "dur": 1.517, + "args": { + "External id": 4731539,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748978.679, "dur": 0.611, + "args": { + "External id": 4731540,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360748979.605, "dur": 38.088, + "args": { + "External id": 4731541,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360748980.546, "dur": 36.231, + "args": { + "External id": 4731542,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749021.134, "dur": 2.200, + "args": { + "External id": 4731543,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749022.537, "dur": 0.726, + "args": { + "External id": 4731544,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749023.615, "dur": 1.921, + "args": { + "External id": 4731545,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749024.529, "dur": 0.941, + "args": { + "External id": 4731546,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749025.781, "dur": 4.255, + "args": { + "External id": 4731547,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749029.116, "dur": 0.852, + "args": { + "External id": 4731548,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749030.320, "dur": 1.977, + "args": { + "External id": 4731549,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749031.258, "dur": 0.970, + "args": { + "External id": 4731550,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749032.577, "dur": 1.854, + "args": { + "External id": 4731551,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749033.694, "dur": 0.670, + "args": { + "External id": 4731552,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749034.687, "dur": 3.111, + "args": { + "External id": 4731553,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749037.155, "dur": 0.578, + "args": { + "External id": 4731554,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749038.068, "dur": 1.926, + "args": { + "External id": 4731555,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749039.143, "dur": 0.784, + "args": { + "External id": 4731556,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749040.241, "dur": 3.179, + "args": { + "External id": 4731557,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749040.938, "dur": 2.416, + "args": { + "External id": 4731558,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749045.822, "dur": 2.221, + "args": { + "External id": 4731559,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749047.283, "dur": 0.679, + "args": { + "External id": 4731560,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749048.317, "dur": 1.507, + "args": { + "External id": 4731561,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749049.208, "dur": 0.554, + "args": { + "External id": 4731562,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749050.092, "dur": 3.711, + "args": { + "External id": 4731563,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749053.157, "dur": 0.580, + "args": { + "External id": 4731564,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749054.074, "dur": 1.531, + "args": { + "External id": 4731565,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749054.941, "dur": 0.594, + "args": { + "External id": 4731566,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749056.047, "dur": 2.241, + "args": { + "External id": 4731567,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749057.348, "dur": 0.874, + "args": { + "External id": 4731568,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749058.563, "dur": 3.319, + "args": { + "External id": 4731569,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749061.041, "dur": 0.777, + "args": { + "External id": 4731570,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749062.116, "dur": 2.107, + "args": { + "External id": 4731571,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749063.349, "dur": 0.807, + "args": { + "External id": 4731572,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749074.789, "dur": 5.038, + "args": { + "External id": 4731573,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749076.161, "dur": 3.446, + "args": { + "External id": 4731574,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749082.114, "dur": 1.598, + "args": { + "External id": 4731575,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749083.147, "dur": 0.498, + "args": { + "External id": 4731576,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749083.982, "dur": 1.678, + "args": { + "External id": 4731577,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749084.868, "dur": 0.723, + "args": { + "External id": 4731578,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749085.917, "dur": 3.425, + "args": { + "External id": 4731579,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749088.780, "dur": 0.496, + "args": { + "External id": 4731580,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749089.609, "dur": 1.643, + "args": { + "External id": 4731581,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749090.476, "dur": 0.700, + "args": { + "External id": 4731582,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749091.480, "dur": 2.016, + "args": { + "External id": 4731583,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749092.727, "dur": 0.700, + "args": { + "External id": 4731584,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749093.740, "dur": 3.713, + "args": { + "External id": 4731585,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749096.650, "dur": 0.740, + "args": { + "External id": 4731586,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749097.918, "dur": 1.664, + "args": { + "External id": 4731587,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749098.884, "dur": 0.626, + "args": { + "External id": 4731588,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749100.024, "dur": 3.449, + "args": { + "External id": 4731589,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749100.720, "dur": 2.492, + "args": { + "External id": 4731590,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749105.915, "dur": 2.227, + "args": { + "External id": 4731591,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749107.326, "dur": 0.750, + "args": { + "External id": 4731592,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749108.396, "dur": 2.051, + "args": { + "External id": 4731593,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749109.521, "dur": 0.859, + "args": { + "External id": 4731594,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749110.780, "dur": 3.834, + "args": { + "External id": 4731595,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749114.005, "dur": 0.542, + "args": { + "External id": 4731596,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749115.005, "dur": 1.380, + "args": { + "External id": 4731597,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749115.717, "dur": 0.596, + "args": { + "External id": 4731598,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749116.830, "dur": 2.430, + "args": { + "External id": 4731599,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749118.162, "dur": 1.030, + "args": { + "External id": 4731600,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749119.530, "dur": 2.870, + "args": { + "External id": 4731601,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749121.763, "dur": 0.573, + "args": { + "External id": 4731602,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749122.663, "dur": 2.223, + "args": { + "External id": 4731603,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749123.983, "dur": 0.836, + "args": { + "External id": 4731604,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749125.354, "dur": 3.068, + "args": { + "External id": 4731605,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749126.007, "dur": 2.344, + "args": { + "External id": 4731606,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749130.786, "dur": 1.725, + "args": { + "External id": 4731607,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749131.852, "dur": 0.597, + "args": { + "External id": 4731608,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749132.754, "dur": 1.772, + "args": { + "External id": 4731609,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749133.733, "dur": 0.726, + "args": { + "External id": 4731610,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749134.752, "dur": 4.039, + "args": { + "External id": 4731611,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749138.140, "dur": 0.584, + "args": { + "External id": 4731612,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749139.055, "dur": 1.416, + "args": { + "External id": 4731613,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749139.682, "dur": 0.725, + "args": { + "External id": 4731614,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749140.697, "dur": 2.027, + "args": { + "External id": 4731615,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749142.003, "dur": 0.650, + "args": { + "External id": 4731616,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749142.967, "dur": 3.596, + "args": { + "External id": 4731617,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749145.616, "dur": 0.885, + "args": { + "External id": 4731618,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749146.790, "dur": 1.734, + "args": { + "External id": 4731619,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749147.883, "dur": 0.574, + "args": { + "External id": 4731620,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749148.765, "dur": 3.245, + "args": { + "External id": 4731621,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749149.442, "dur": 2.266, + "args": { + "External id": 4731622,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749154.652, "dur": 2.046, + "args": { + "External id": 4731623,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749156.062, "dur": 0.571, + "args": { + "External id": 4731624,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749157.296, "dur": 1.720, + "args": { + "External id": 4731625,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749158.159, "dur": 0.790, + "args": { + "External id": 4731626,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749159.267, "dur": 4.695, + "args": { + "External id": 4731627,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749163.125, "dur": 0.770, + "args": { + "External id": 4731628,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749164.250, "dur": 1.550, + "args": { + "External id": 4731629,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749164.938, "dur": 0.798, + "args": { + "External id": 4731630,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749166.023, "dur": 2.551, + "args": { + "External id": 4731631,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749167.627, "dur": 0.879, + "args": { + "External id": 4731632,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749168.830, "dur": 3.649, + "args": { + "External id": 4731633,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749171.424, "dur": 0.987, + "args": { + "External id": 4731634,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749172.712, "dur": 1.670, + "args": { + "External id": 4731635,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749173.580, "dur": 0.739, + "args": { + "External id": 4731636,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749174.622, "dur": 3.094, + "args": { + "External id": 4731637,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749175.243, "dur": 2.403, + "args": { + "External id": 4731638,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749180.182, "dur": 1.941, + "args": { + "External id": 4731639,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749181.214, "dur": 0.844, + "args": { + "External id": 4731640,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749182.367, "dur": 1.442, + "args": { + "External id": 4731641,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749183.013, "dur": 0.727, + "args": { + "External id": 4731642,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749184.095, "dur": 3.986, + "args": { + "External id": 4731643,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749187.136, "dur": 0.878, + "args": { + "External id": 4731644,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749188.368, "dur": 1.282, + "args": { + "External id": 4731645,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749189.011, "dur": 0.573, + "args": { + "External id": 4731646,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749189.875, "dur": 2.107, + "args": { + "External id": 4731647,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749191.070, "dur": 0.843, + "args": { + "External id": 4731648,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749192.222, "dur": 3.162, + "args": { + "External id": 4731649,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749194.762, "dur": 0.559, + "args": { + "External id": 4731650,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749195.622, "dur": 1.708, + "args": { + "External id": 4731651,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749196.680, "dur": 0.585, + "args": { + "External id": 4731652,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749197.657, "dur": 3.457, + "args": { + "External id": 4731653,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749198.560, "dur": 2.277, + "args": { + "External id": 4731654,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749203.349, "dur": 2.098, + "args": { + "External id": 4731655,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749204.689, "dur": 0.686, + "args": { + "External id": 4731656,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749205.908, "dur": 1.457, + "args": { + "External id": 4731657,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749206.533, "dur": 0.762, + "args": { + "External id": 4731658,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749207.588, "dur": 3.769, + "args": { + "External id": 4731659,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749210.531, "dur": 0.756, + "args": { + "External id": 4731660,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749211.645, "dur": 1.405, + "args": { + "External id": 4731661,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749212.291, "dur": 0.686, + "args": { + "External id": 4731662,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749213.273, "dur": 1.795, + "args": { + "External id": 4731663,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749214.329, "dur": 0.672, + "args": { + "External id": 4731664,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749215.334, "dur": 3.529, + "args": { + "External id": 4731665,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749218.080, "dur": 0.717, + "args": { + "External id": 4731666,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749219.087, "dur": 1.844, + "args": { + "External id": 4731667,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749220.213, "dur": 0.651, + "args": { + "External id": 4731668,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749221.258, "dur": 3.797, + "args": { + "External id": 4731669,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749222.327, "dur": 2.656, + "args": { + "External id": 4731670,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749227.292, "dur": 2.302, + "args": { + "External id": 4731671,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749228.787, "dur": 0.740, + "args": { + "External id": 4731672,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749229.835, "dur": 1.752, + "args": { + "External id": 4731673,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749230.780, "dur": 0.740, + "args": { + "External id": 4731674,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749232.063, "dur": 4.245, + "args": { + "External id": 4731675,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749235.406, "dur": 0.838, + "args": { + "External id": 4731676,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749236.704, "dur": 1.507, + "args": { + "External id": 4731677,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749237.559, "dur": 0.587, + "args": { + "External id": 4731678,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749238.434, "dur": 1.894, + "args": { + "External id": 4731679,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749239.541, "dur": 0.721, + "args": { + "External id": 4731680,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749240.780, "dur": 3.177, + "args": { + "External id": 4731681,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749243.277, "dur": 0.615, + "args": { + "External id": 4731682,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749244.200, "dur": 1.946, + "args": { + "External id": 4731683,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749245.462, "dur": 0.618, + "args": { + "External id": 4731684,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749246.387, "dur": 3.673, + "args": { + "External id": 4731685,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749247.256, "dur": 2.729, + "args": { + "External id": 4731686,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749252.481, "dur": 2.085, + "args": { + "External id": 4731687,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749253.750, "dur": 0.749, + "args": { + "External id": 4731688,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749254.847, "dur": 1.524, + "args": { + "External id": 4731689,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749255.687, "dur": 0.615, + "args": { + "External id": 4731690,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749256.597, "dur": 4.331, + "args": { + "External id": 4731691,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749260.240, "dur": 0.618, + "args": { + "External id": 4731692,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749261.311, "dur": 1.944, + "args": { + "External id": 4731693,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749262.425, "dur": 0.764, + "args": { + "External id": 4731694,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749263.476, "dur": 2.095, + "args": { + "External id": 4731695,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749264.635, "dur": 0.868, + "args": { + "External id": 4731696,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749266.001, "dur": 2.878, + "args": { + "External id": 4731697,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749268.070, "dur": 0.740, + "args": { + "External id": 4731698,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749269.102, "dur": 1.906, + "args": { + "External id": 4731699,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749270.227, "dur": 0.717, + "args": { + "External id": 4731700,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749271.248, "dur": 3.179, + "args": { + "External id": 4731701,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749272.109, "dur": 2.246, + "args": { + "External id": 4731702,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749276.537, "dur": 1.985, + "args": { + "External id": 4731703,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749277.881, "dur": 0.576, + "args": { + "External id": 4731704,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749279.026, "dur": 1.776, + "args": { + "External id": 4731705,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749279.873, "dur": 0.862, + "args": { + "External id": 4731706,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749281.026, "dur": 4.142, + "args": { + "External id": 4731707,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749284.336, "dur": 0.764, + "args": { + "External id": 4731708,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749285.837, "dur": 1.620, + "args": { + "External id": 4731709,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749286.498, "dur": 0.892, + "args": { + "External id": 4731710,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749287.705, "dur": 1.923, + "args": { + "External id": 4731711,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749288.750, "dur": 0.807, + "args": { + "External id": 4731712,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749290.064, "dur": 3.224, + "args": { + "External id": 4731713,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749292.410, "dur": 0.805, + "args": { + "External id": 4731714,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749293.572, "dur": 1.983, + "args": { + "External id": 4731715,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749294.625, "dur": 0.866, + "args": { + "External id": 4731716,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749295.996, "dur": 3.577, + "args": { + "External id": 4731717,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749297.073, "dur": 2.428, + "args": { + "External id": 4731718,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749301.632, "dur": 2.545, + "args": { + "External id": 4731719,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749303.230, "dur": 0.879, + "args": { + "External id": 4731720,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749304.439, "dur": 1.960, + "args": { + "External id": 4731721,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749305.296, "dur": 1.037, + "args": { + "External id": 4731722,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749306.622, "dur": 3.980, + "args": { + "External id": 4731723,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749309.780, "dur": 0.756, + "args": { + "External id": 4731724,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749310.863, "dur": 1.699, + "args": { + "External id": 4731725,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749311.735, "dur": 0.757, + "args": { + "External id": 4731726,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749312.963, "dur": 2.222, + "args": { + "External id": 4731727,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749314.234, "dur": 0.879, + "args": { + "External id": 4731728,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749315.426, "dur": 2.897, + "args": { + "External id": 4731729,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749317.670, "dur": 0.589, + "args": { + "External id": 4731730,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749318.775, "dur": 2.242, + "args": { + "External id": 4731731,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749320.250, "dur": 0.701, + "args": { + "External id": 4731732,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749321.439, "dur": 2.924, + "args": { + "External id": 4731733,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749322.108, "dur": 1.997, + "args": { + "External id": 4731734,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749326.563, "dur": 1.845, + "args": { + "External id": 4731735,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749327.727, "dur": 0.619, + "args": { + "External id": 4731736,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749328.647, "dur": 2.002, + "args": { + "External id": 4731737,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749329.888, "dur": 0.695, + "args": { + "External id": 4731738,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749331.063, "dur": 3.569, + "args": { + "External id": 4731739,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749333.996, "dur": 0.566, + "args": { + "External id": 4731740,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749335.068, "dur": 1.698, + "args": { + "External id": 4731741,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749335.897, "dur": 0.801, + "args": { + "External id": 4731742,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749336.989, "dur": 1.859, + "args": { + "External id": 4731743,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749337.891, "dur": 0.890, + "args": { + "External id": 4731744,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749339.088, "dur": 3.422, + "args": { + "External id": 4731745,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749341.683, "dur": 0.758, + "args": { + "External id": 4731746,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749342.733, "dur": 1.646, + "args": { + "External id": 4731747,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749343.886, "dur": 0.425, + "args": { + "External id": 4731748,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749344.618, "dur": 2.997, + "args": { + "External id": 4731749,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749345.258, "dur": 2.095, + "args": { + "External id": 4731750,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749350.142, "dur": 1.894, + "args": { + "External id": 4731751,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749351.175, "dur": 0.795, + "args": { + "External id": 4731752,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749352.494, "dur": 1.787, + "args": { + "External id": 4731753,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749353.369, "dur": 0.845, + "args": { + "External id": 4731754,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749354.640, "dur": 4.814, + "args": { + "External id": 4731755,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749358.487, "dur": 0.906, + "args": { + "External id": 4731756,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749359.737, "dur": 1.803, + "args": { + "External id": 4731757,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749360.687, "dur": 0.787, + "args": { + "External id": 4731758,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749361.926, "dur": 2.157, + "args": { + "External id": 4731759,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749363.159, "dur": 0.856, + "args": { + "External id": 4731760,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749364.368, "dur": 3.075, + "args": { + "External id": 4731761,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749366.733, "dur": 0.646, + "args": { + "External id": 4731762,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749367.667, "dur": 1.887, + "args": { + "External id": 4731763,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749368.753, "dur": 0.739, + "args": { + "External id": 4731764,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749370.176, "dur": 3.413, + "args": { + "External id": 4731765,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749370.996, "dur": 2.523, + "args": { + "External id": 4731766,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749375.818, "dur": 1.896, + "args": { + "External id": 4731767,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749377.041, "dur": 0.607, + "args": { + "External id": 4731768,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749378.138, "dur": 1.837, + "args": { + "External id": 4731769,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749379.238, "dur": 0.668, + "args": { + "External id": 4731770,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749380.225, "dur": 3.724, + "args": { + "External id": 4731771,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749383.150, "dur": 0.732, + "args": { + "External id": 4731772,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749384.410, "dur": 1.515, + "args": { + "External id": 4731773,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749385.088, "dur": 0.771, + "args": { + "External id": 4731774,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749386.342, "dur": 2.056, + "args": { + "External id": 4731775,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749387.481, "dur": 0.846, + "args": { + "External id": 4731776,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749388.662, "dur": 3.139, + "args": { + "External id": 4731777,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749391.169, "dur": 0.563, + "args": { + "External id": 4731778,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1712360749392.025, "dur": 3.320, + "args": { + "External id": 4731779,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749394.674, "dur": 0.606, + "args": { + "External id": 4731780,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 1336753, "tid": 1336753, + "ts": 1712360749419.839, "dur": 131.083, + "args": { + "External id": 4731781,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 1336753, "tid": 1336753, + "ts": 1712360749656.630, "dur": 134.545, + "args": { + "External id": 4731782,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[291], [], [], [], []], "Ev Idx": 11293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 1336753, "tid": 1336753, + "ts": 1712360749723.229, "dur": 48.416, + "args": { + "External id": 4731783,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[291], [], [], [], []], "Ev Idx": 11294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1712360749736.080, "dur": 1.079, + "args": { + "External id": 4731784,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Redistribute", "pid": 1336753, "tid": 1336753, + "ts": 1712360750326.444, "dur": 1021.531, + "args": { + "External id": 4731785,"Sequence number": 47019000, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "False"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 1336753, "tid": 1336753, + "ts": 1712360750390.867, "dur": 128.575, + "args": { + "External id": 4731786,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360750396.542, "dur": 1.404, + "args": { + "External id": 4731787,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360750467.294, "dur": 0.964, + "args": { + "External id": 4731788,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 1336753, "tid": 1336753, + "ts": 1712360750549.078, "dur": 425.525, + "args": { + "External id": 4731789,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1712360750552.814, "dur": 48.244, + "args": { + "External id": 4731790,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1712360750556.066, "dur": 10.099, + "args": { + "External id": 4731791,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712360750562.113, "dur": 3.340, + "args": { + "External id": 4731792,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1712360750567.604, "dur": 32.756, + "args": { + "External id": 4731793,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 1336753, "tid": 1336753, + "ts": 1712360750610.444, "dur": 360.789, + "args": { + "External id": 4731794,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[]], [], [], [], []], "Input Dims": [[[]], [], [], [], []], "Ev Idx": 11305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712360750643.085, "dur": 322.562, + "args": { + "External id": 4731795,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 11306, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 1336753, "tid": 1336753, + "ts": 1712360750659.079, "dur": 301.007, + "args": { + "External id": 4731796,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 1336753, "tid": 1336753, + "ts": 1712360751094.301, "dur": 215.894, + "args": { + "External id": 4731797,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 1336753, "tid": 1336753, + "ts": 1712360751194.949, "dur": 34.540, + "args": { + "External id": 4731798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1712360751214.978, "dur": 4.939, + "args": { + "External id": 4731799,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11310, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 1336753, "tid": 1336753, + "ts": 1712360751259.072, "dur": 44.901, + "args": { + "External id": 4731800,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360751261.879, "dur": 1.167, + "args": { + "External id": 4731801,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360751264.652, "dur": 0.605, + "args": { + "External id": 4731802,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_ToTorchTensor", "pid": 1336753, "tid": 1336753, + "ts": 1712360751375.684, "dur": 27.535, + "args": { + "External id": 4731803,"Sequence number": 47019001, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1712360751389.547, "dur": 9.433, + "args": { + "External id": 4731804,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1712360751392.328, "dur": 6.446, + "args": { + "External id": 4731805,"Record function id": 0, "Concrete Inputs": ["", "[]"], "Input type": ["float", "ScalarList"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1712360751811.461, "dur": 38.308, + "args": { + "External id": 4731806,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "double", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reciprocal", "pid": 1336753, "tid": 1336753, + "ts": 1712360751860.483, "dur": 23.857, + "args": { + "External id": 4731807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mul", "pid": 1336753, "tid": 1336753, + "ts": 1712360751891.941, "dur": 23.099, + "args": { + "External id": 4731808,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "double"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clamp", "pid": 1336753, "tid": 1336753, + "ts": 1712360751927.242, "dur": 25.517, + "args": { + "External id": 4731809,"Record function id": 0, "Concrete Inputs": ["", "", "1."], "Input type": ["float", "", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360751929.933, "dur": 0.718, + "args": { + "External id": 4731810,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1712360751969.611, "dur": 0.653, + "args": { + "External id": 4731811,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 11322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 1336753, "tid": 1336753, + "ts": 1712360752150.428, "dur": 812.356, + "args": { + "External id": 4731812,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 1336753, "tid": 1336753, + "ts": 1712360752658.515, "dur": 273.488, + "args": { + "External id": 4731813,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isnan", "pid": 1336753, "tid": 1336753, + "ts": 1712360753039.476, "dur": 49.322, + "args": { + "External id": 4731814,"Sequence number": 47019002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1712360753043.624, "dur": 44.118, + "args": { + "External id": 4731815,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336753, "tid": 1336753, + "ts": 1712360753093.419, "dur": 155.148, + "args": { + "External id": 4731816,"Sequence number": 47019002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1712360753095.371, "dur": 153.017, + "args": { + "External id": 4731817,"Sequence number": 47019002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1712360753097.373, "dur": 150.626, + "args": { + "External id": 4731818,"Sequence number": 47019002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isinf", "pid": 1336753, "tid": 1336753, + "ts": 1712360753253.752, "dur": 63.644, + "args": { + "External id": 4731819,"Sequence number": 47019002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712360753256.396, "dur": 36.329, + "args": { + "External id": 4731820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1712360753262.834, "dur": 2.875, + "args": { + "External id": 4731821,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1712360753267.104, "dur": 25.291, + "args": { + "External id": 4731822,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], [1]], "Input Dims": [[], [0]], "Ev Idx": 11333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1712360753274.345, "dur": 2.444, + "args": { + "External id": 4731823,"Record function id": 0, "Concrete Inputs": ["", "[]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 11334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1712360753294.601, "dur": 21.987, + "args": { + "External id": 4731824,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336753, "tid": 1336753, + "ts": 1712360753319.570, "dur": 33.816, + "args": { + "External id": 4731825,"Sequence number": 47019002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1712360753320.068, "dur": 33.172, + "args": { + "External id": 4731826,"Sequence number": 47019002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1712360753321.069, "dur": 31.861, + "args": { + "External id": 4731827,"Sequence number": 47019002, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11338 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#OptimizersContainer.step", "pid": 1336753, "tid": 1336753, + "ts": 1712360753384.670, "dur": 6372.648, + "args": { + "External id": 4731828,"Record function id": 0, "Ev Idx": 11339 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 1336753, "tid": 1336753, + "ts": 1712360753419.839, "dur": 6311.973, + "args": { + "External id": 4731829,"Record function id": 0, "Ev Idx": 11340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 1336753, "tid": 1336753, + "ts": 1712360754862.348, "dur": 430.798, + "args": { + "External id": 4731830,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754882.254, "dur": 1.006, + "args": { + "External id": 4731831,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754884.190, "dur": 0.417, + "args": { + "External id": 4731832,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754885.373, "dur": 0.073, + "args": { + "External id": 4731833,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754885.936, "dur": 0.069, + "args": { + "External id": 4731834,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754886.548, "dur": 0.465, + "args": { + "External id": 4731835,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754887.406, "dur": 0.067, + "args": { + "External id": 4731836,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754887.999, "dur": 0.103, + "args": { + "External id": 4731837,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754888.564, "dur": 0.163, + "args": { + "External id": 4731838,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754889.188, "dur": 0.048, + "args": { + "External id": 4731839,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754889.640, "dur": 0.088, + "args": { + "External id": 4731840,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754890.055, "dur": 0.151, + "args": { + "External id": 4731841,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754890.647, "dur": 0.076, + "args": { + "External id": 4731842,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754891.292, "dur": 0.100, + "args": { + "External id": 4731843,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754891.856, "dur": 0.055, + "args": { + "External id": 4731844,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754892.393, "dur": 0.060, + "args": { + "External id": 4731845,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754892.906, "dur": 0.056, + "args": { + "External id": 4731846,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754893.418, "dur": 0.067, + "args": { + "External id": 4731847,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754893.813, "dur": 0.058, + "args": { + "External id": 4731848,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754894.234, "dur": 0.058, + "args": { + "External id": 4731849,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754895.069, "dur": 0.056, + "args": { + "External id": 4731850,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754895.516, "dur": 0.055, + "args": { + "External id": 4731851,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754895.947, "dur": 0.057, + "args": { + "External id": 4731852,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754896.564, "dur": 0.055, + "args": { + "External id": 4731853,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754897.093, "dur": 0.068, + "args": { + "External id": 4731854,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754897.633, "dur": 0.080, + "args": { + "External id": 4731855,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754898.162, "dur": 0.055, + "args": { + "External id": 4731856,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754898.743, "dur": 0.058, + "args": { + "External id": 4731857,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754899.350, "dur": 0.057, + "args": { + "External id": 4731858,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754899.915, "dur": 0.057, + "args": { + "External id": 4731859,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754900.630, "dur": 0.063, + "args": { + "External id": 4731860,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754901.358, "dur": 0.056, + "args": { + "External id": 4731861,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754901.908, "dur": 0.057, + "args": { + "External id": 4731862,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754902.323, "dur": 0.069, + "args": { + "External id": 4731863,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754902.746, "dur": 0.057, + "args": { + "External id": 4731864,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754903.126, "dur": 0.066, + "args": { + "External id": 4731865,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754903.745, "dur": 0.069, + "args": { + "External id": 4731866,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754904.410, "dur": 0.096, + "args": { + "External id": 4731867,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754904.872, "dur": 0.173, + "args": { + "External id": 4731868,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754905.460, "dur": 0.060, + "args": { + "External id": 4731869,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754906.062, "dur": 0.060, + "args": { + "External id": 4731870,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754906.499, "dur": 0.059, + "args": { + "External id": 4731871,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754907.005, "dur": 0.093, + "args": { + "External id": 4731872,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754907.357, "dur": 0.067, + "args": { + "External id": 4731873,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754907.903, "dur": 0.080, + "args": { + "External id": 4731874,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754908.495, "dur": 0.063, + "args": { + "External id": 4731875,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754909.038, "dur": 0.060, + "args": { + "External id": 4731876,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754909.591, "dur": 0.176, + "args": { + "External id": 4731877,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754910.152, "dur": 0.059, + "args": { + "External id": 4731878,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754910.578, "dur": 0.057, + "args": { + "External id": 4731879,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754911.102, "dur": 0.056, + "args": { + "External id": 4731880,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754911.631, "dur": 0.059, + "args": { + "External id": 4731881,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754912.105, "dur": 0.051, + "args": { + "External id": 4731882,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754912.899, "dur": 0.067, + "args": { + "External id": 4731883,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754913.263, "dur": 0.059, + "args": { + "External id": 4731884,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754913.692, "dur": 0.069, + "args": { + "External id": 4731885,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754914.103, "dur": 0.068, + "args": { + "External id": 4731886,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754914.614, "dur": 0.066, + "args": { + "External id": 4731887,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754915.035, "dur": 0.069, + "args": { + "External id": 4731888,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754915.524, "dur": 0.067, + "args": { + "External id": 4731889,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754915.994, "dur": 0.070, + "args": { + "External id": 4731890,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754916.576, "dur": 0.057, + "args": { + "External id": 4731891,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754917.067, "dur": 0.094, + "args": { + "External id": 4731892,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754917.736, "dur": 0.080, + "args": { + "External id": 4731893,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754918.164, "dur": 0.094, + "args": { + "External id": 4731894,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754918.548, "dur": 0.058, + "args": { + "External id": 4731895,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754918.910, "dur": 0.064, + "args": { + "External id": 4731896,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754919.465, "dur": 0.143, + "args": { + "External id": 4731897,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754919.958, "dur": 0.069, + "args": { + "External id": 4731898,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754920.445, "dur": 0.062, + "args": { + "External id": 4731899,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754920.857, "dur": 0.202, + "args": { + "External id": 4731900,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754921.536, "dur": 0.061, + "args": { + "External id": 4731901,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754922.380, "dur": 0.169, + "args": { + "External id": 4731902,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754923.078, "dur": 0.056, + "args": { + "External id": 4731903,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360754923.614, "dur": 0.077, + "args": { + "External id": 4731904,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755034.537, "dur": 0.645, + "args": { + "External id": 4731905,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755037.695, "dur": 0.047, + "args": { + "External id": 4731906,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755038.218, "dur": 0.048, + "args": { + "External id": 4731907,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755038.805, "dur": 0.070, + "args": { + "External id": 4731908,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755039.211, "dur": 0.049, + "args": { + "External id": 4731909,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755039.722, "dur": 0.053, + "args": { + "External id": 4731910,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755040.342, "dur": 0.062, + "args": { + "External id": 4731911,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755040.965, "dur": 0.061, + "args": { + "External id": 4731912,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755041.365, "dur": 0.056, + "args": { + "External id": 4731913,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755041.859, "dur": 0.048, + "args": { + "External id": 4731914,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755042.259, "dur": 0.059, + "args": { + "External id": 4731915,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755042.698, "dur": 0.056, + "args": { + "External id": 4731916,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755043.147, "dur": 0.071, + "args": { + "External id": 4731917,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755043.585, "dur": 0.056, + "args": { + "External id": 4731918,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755044.016, "dur": 0.064, + "args": { + "External id": 4731919,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755044.493, "dur": 0.062, + "args": { + "External id": 4731920,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755044.919, "dur": 0.061, + "args": { + "External id": 4731921,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755045.929, "dur": 0.063, + "args": { + "External id": 4731922,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755046.518, "dur": 0.052, + "args": { + "External id": 4731923,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755047.113, "dur": 0.058, + "args": { + "External id": 4731924,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755047.693, "dur": 0.051, + "args": { + "External id": 4731925,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755048.158, "dur": 0.055, + "args": { + "External id": 4731926,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755048.669, "dur": 0.055, + "args": { + "External id": 4731927,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755049.010, "dur": 0.062, + "args": { + "External id": 4731928,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755049.567, "dur": 0.054, + "args": { + "External id": 4731929,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755049.891, "dur": 0.060, + "args": { + "External id": 4731930,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755050.491, "dur": 0.067, + "args": { + "External id": 4731931,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755051.087, "dur": 0.058, + "args": { + "External id": 4731932,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755051.722, "dur": 0.054, + "args": { + "External id": 4731933,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755052.111, "dur": 0.052, + "args": { + "External id": 4731934,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755052.583, "dur": 0.057, + "args": { + "External id": 4731935,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755053.098, "dur": 0.045, + "args": { + "External id": 4731936,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755053.455, "dur": 0.054, + "args": { + "External id": 4731937,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755053.850, "dur": 0.058, + "args": { + "External id": 4731938,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755054.557, "dur": 0.060, + "args": { + "External id": 4731939,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755054.953, "dur": 0.060, + "args": { + "External id": 4731940,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755055.466, "dur": 0.056, + "args": { + "External id": 4731941,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755055.983, "dur": 0.066, + "args": { + "External id": 4731942,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755056.737, "dur": 0.058, + "args": { + "External id": 4731943,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755057.188, "dur": 0.067, + "args": { + "External id": 4731944,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755057.769, "dur": 0.062, + "args": { + "External id": 4731945,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755058.343, "dur": 0.059, + "args": { + "External id": 4731946,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755058.774, "dur": 0.058, + "args": { + "External id": 4731947,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755059.279, "dur": 0.057, + "args": { + "External id": 4731948,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755059.701, "dur": 0.065, + "args": { + "External id": 4731949,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755060.319, "dur": 0.065, + "args": { + "External id": 4731950,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755060.742, "dur": 0.062, + "args": { + "External id": 4731951,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755061.124, "dur": 0.066, + "args": { + "External id": 4731952,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755061.629, "dur": 0.067, + "args": { + "External id": 4731953,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755061.986, "dur": 0.057, + "args": { + "External id": 4731954,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755062.403, "dur": 0.057, + "args": { + "External id": 4731955,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755062.926, "dur": 0.056, + "args": { + "External id": 4731956,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755063.353, "dur": 0.060, + "args": { + "External id": 4731957,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755101.770, "dur": 0.454, + "args": { + "External id": 4731958,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755105.119, "dur": 0.062, + "args": { + "External id": 4731959,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755105.568, "dur": 0.067, + "args": { + "External id": 4731960,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755106.008, "dur": 0.058, + "args": { + "External id": 4731961,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755106.419, "dur": 0.051, + "args": { + "External id": 4731962,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755106.819, "dur": 0.065, + "args": { + "External id": 4731963,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755107.248, "dur": 0.054, + "args": { + "External id": 4731964,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755108.147, "dur": 0.053, + "args": { + "External id": 4731965,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755108.673, "dur": 0.067, + "args": { + "External id": 4731966,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755109.071, "dur": 0.059, + "args": { + "External id": 4731967,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755109.494, "dur": 0.068, + "args": { + "External id": 4731968,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755110.024, "dur": 0.062, + "args": { + "External id": 4731969,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755110.661, "dur": 0.071, + "args": { + "External id": 4731970,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755111.075, "dur": 0.061, + "args": { + "External id": 4731971,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755111.588, "dur": 0.056, + "args": { + "External id": 4731972,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755112.001, "dur": 0.056, + "args": { + "External id": 4731973,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755112.410, "dur": 0.058, + "args": { + "External id": 4731974,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755112.998, "dur": 0.057, + "args": { + "External id": 4731975,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755113.535, "dur": 0.055, + "args": { + "External id": 4731976,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755113.973, "dur": 0.067, + "args": { + "External id": 4731977,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755114.492, "dur": 0.066, + "args": { + "External id": 4731978,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755114.926, "dur": 0.092, + "args": { + "External id": 4731979,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755115.424, "dur": 0.053, + "args": { + "External id": 4731980,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755116.128, "dur": 0.045, + "args": { + "External id": 4731981,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755116.877, "dur": 0.065, + "args": { + "External id": 4731982,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755117.484, "dur": 0.055, + "args": { + "External id": 4731983,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755118.031, "dur": 0.064, + "args": { + "External id": 4731984,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755118.642, "dur": 0.067, + "args": { + "External id": 4731985,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755119.148, "dur": 0.067, + "args": { + "External id": 4731986,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755119.512, "dur": 0.068, + "args": { + "External id": 4731987,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755120.179, "dur": 0.056, + "args": { + "External id": 4731988,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755120.751, "dur": 0.068, + "args": { + "External id": 4731989,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755121.100, "dur": 0.064, + "args": { + "External id": 4731990,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755121.730, "dur": 0.069, + "args": { + "External id": 4731991,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755122.234, "dur": 0.065, + "args": { + "External id": 4731992,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755122.821, "dur": 0.052, + "args": { + "External id": 4731993,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755123.174, "dur": 0.064, + "args": { + "External id": 4731994,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755123.792, "dur": 0.054, + "args": { + "External id": 4731995,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755124.396, "dur": 0.052, + "args": { + "External id": 4731996,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755124.974, "dur": 0.058, + "args": { + "External id": 4731997,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755125.401, "dur": 0.058, + "args": { + "External id": 4731998,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755125.921, "dur": 0.065, + "args": { + "External id": 4731999,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755126.424, "dur": 0.063, + "args": { + "External id": 4732000,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755127.230, "dur": 0.058, + "args": { + "External id": 4732001,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755127.672, "dur": 0.068, + "args": { + "External id": 4732002,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755128.073, "dur": 0.064, + "args": { + "External id": 4732003,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755128.607, "dur": 0.067, + "args": { + "External id": 4732004,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755129.227, "dur": 0.062, + "args": { + "External id": 4732005,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755129.750, "dur": 0.064, + "args": { + "External id": 4732006,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755130.233, "dur": 0.066, + "args": { + "External id": 4732007,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755130.891, "dur": 0.055, + "args": { + "External id": 4732008,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755131.464, "dur": 0.049, + "args": { + "External id": 4732009,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755131.885, "dur": 0.059, + "args": { + "External id": 4732010,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755132.304, "dur": 0.064, + "args": { + "External id": 4732011,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755132.738, "dur": 0.061, + "args": { + "External id": 4732012,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755133.576, "dur": 0.070, + "args": { + "External id": 4732013,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755134.157, "dur": 0.064, + "args": { + "External id": 4732014,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755134.711, "dur": 0.062, + "args": { + "External id": 4732015,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755135.441, "dur": 0.053, + "args": { + "External id": 4732016,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755135.755, "dur": 0.057, + "args": { + "External id": 4732017,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755136.142, "dur": 0.061, + "args": { + "External id": 4732018,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755136.696, "dur": 0.058, + "args": { + "External id": 4732019,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755137.208, "dur": 0.052, + "args": { + "External id": 4732020,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755137.807, "dur": 0.065, + "args": { + "External id": 4732021,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755138.202, "dur": 0.068, + "args": { + "External id": 4732022,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755138.717, "dur": 0.050, + "args": { + "External id": 4732023,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755139.223, "dur": 0.057, + "args": { + "External id": 4732024,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755139.639, "dur": 0.060, + "args": { + "External id": 4732025,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755140.597, "dur": 0.060, + "args": { + "External id": 4732026,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755141.040, "dur": 0.064, + "args": { + "External id": 4732027,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755141.607, "dur": 0.054, + "args": { + "External id": 4732028,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755142.189, "dur": 0.071, + "args": { + "External id": 4732029,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755142.669, "dur": 0.065, + "args": { + "External id": 4732030,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755143.357, "dur": 0.056, + "args": { + "External id": 4732031,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755143.884, "dur": 0.056, + "args": { + "External id": 4732032,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755144.224, "dur": 0.066, + "args": { + "External id": 4732033,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755144.953, "dur": 0.060, + "args": { + "External id": 4732034,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755145.534, "dur": 0.066, + "args": { + "External id": 4732035,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755146.056, "dur": 0.066, + "args": { + "External id": 4732036,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755146.629, "dur": 0.064, + "args": { + "External id": 4732037,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755147.176, "dur": 0.060, + "args": { + "External id": 4732038,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755147.838, "dur": 0.069, + "args": { + "External id": 4732039,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755148.285, "dur": 0.088, + "args": { + "External id": 4732040,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755148.753, "dur": 0.054, + "args": { + "External id": 4732041,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755149.266, "dur": 0.067, + "args": { + "External id": 4732042,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755149.698, "dur": 0.056, + "args": { + "External id": 4732043,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755150.119, "dur": 0.058, + "args": { + "External id": 4732044,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755150.561, "dur": 0.054, + "args": { + "External id": 4732045,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755151.293, "dur": 0.051, + "args": { + "External id": 4732046,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755151.881, "dur": 0.067, + "args": { + "External id": 4732047,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755152.429, "dur": 0.056, + "args": { + "External id": 4732048,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755152.922, "dur": 0.056, + "args": { + "External id": 4732049,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755153.488, "dur": 0.068, + "args": { + "External id": 4732050,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755153.881, "dur": 0.071, + "args": { + "External id": 4732051,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755154.510, "dur": 0.058, + "args": { + "External id": 4732052,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755155.134, "dur": 0.059, + "args": { + "External id": 4732053,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755155.645, "dur": 0.047, + "args": { + "External id": 4732054,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755156.291, "dur": 0.055, + "args": { + "External id": 4732055,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755156.867, "dur": 0.066, + "args": { + "External id": 4732056,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755157.589, "dur": 0.072, + "args": { + "External id": 4732057,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755157.977, "dur": 0.047, + "args": { + "External id": 4732058,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755158.288, "dur": 0.061, + "args": { + "External id": 4732059,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755158.623, "dur": 0.058, + "args": { + "External id": 4732060,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755159.560, "dur": 0.054, + "args": { + "External id": 4732061,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755159.939, "dur": 0.052, + "args": { + "External id": 4732062,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755160.514, "dur": 0.058, + "args": { + "External id": 4732063,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755160.846, "dur": 0.049, + "args": { + "External id": 4732064,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755161.624, "dur": 0.055, + "args": { + "External id": 4732065,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755161.932, "dur": 0.047, + "args": { + "External id": 4732066,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755162.492, "dur": 0.060, + "args": { + "External id": 4732067,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755162.801, "dur": 0.053, + "args": { + "External id": 4732068,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755163.385, "dur": 0.057, + "args": { + "External id": 4732069,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755163.695, "dur": 0.047, + "args": { + "External id": 4732070,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755164.470, "dur": 0.067, + "args": { + "External id": 4732071,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755164.792, "dur": 0.052, + "args": { + "External id": 4732072,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755165.658, "dur": 0.057, + "args": { + "External id": 4732073,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755165.964, "dur": 0.055, + "args": { + "External id": 4732074,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755166.744, "dur": 0.061, + "args": { + "External id": 4732075,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755167.055, "dur": 0.055, + "args": { + "External id": 4732076,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755167.885, "dur": 0.059, + "args": { + "External id": 4732077,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755168.221, "dur": 0.049, + "args": { + "External id": 4732078,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755168.991, "dur": 0.059, + "args": { + "External id": 4732079,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755169.303, "dur": 0.055, + "args": { + "External id": 4732080,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755169.965, "dur": 0.056, + "args": { + "External id": 4732081,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755170.301, "dur": 0.049, + "args": { + "External id": 4732082,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755170.928, "dur": 0.057, + "args": { + "External id": 4732083,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755171.244, "dur": 0.049, + "args": { + "External id": 4732084,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755171.830, "dur": 0.057, + "args": { + "External id": 4732085,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755172.142, "dur": 0.048, + "args": { + "External id": 4732086,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755172.961, "dur": 0.057, + "args": { + "External id": 4732087,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755173.272, "dur": 0.050, + "args": { + "External id": 4732088,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755174.166, "dur": 0.050, + "args": { + "External id": 4732089,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755174.468, "dur": 0.050, + "args": { + "External id": 4732090,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755175.260, "dur": 0.058, + "args": { + "External id": 4732091,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755175.571, "dur": 0.051, + "args": { + "External id": 4732092,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755176.382, "dur": 0.056, + "args": { + "External id": 4732093,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755176.691, "dur": 0.049, + "args": { + "External id": 4732094,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755177.520, "dur": 0.067, + "args": { + "External id": 4732095,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755177.842, "dur": 0.050, + "args": { + "External id": 4732096,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755178.649, "dur": 0.063, + "args": { + "External id": 4732097,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755178.962, "dur": 0.051, + "args": { + "External id": 4732098,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755180.001, "dur": 0.056, + "args": { + "External id": 4732099,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755180.309, "dur": 0.049, + "args": { + "External id": 4732100,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755180.885, "dur": 0.059, + "args": { + "External id": 4732101,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755181.193, "dur": 0.049, + "args": { + "External id": 4732102,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755181.774, "dur": 0.070, + "args": { + "External id": 4732103,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755182.093, "dur": 0.050, + "args": { + "External id": 4732104,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755182.925, "dur": 0.059, + "args": { + "External id": 4732105,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755183.233, "dur": 0.048, + "args": { + "External id": 4732106,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755183.785, "dur": 0.055, + "args": { + "External id": 4732107,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755184.154, "dur": 0.047, + "args": { + "External id": 4732108,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755184.972, "dur": 0.060, + "args": { + "External id": 4732109,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755185.281, "dur": 0.051, + "args": { + "External id": 4732110,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755185.878, "dur": 0.059, + "args": { + "External id": 4732111,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755186.373, "dur": 0.060, + "args": { + "External id": 4732112,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755187.190, "dur": 0.058, + "args": { + "External id": 4732113,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755187.498, "dur": 0.050, + "args": { + "External id": 4732114,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755188.112, "dur": 0.060, + "args": { + "External id": 4732115,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755188.422, "dur": 0.050, + "args": { + "External id": 4732116,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755189.197, "dur": 0.059, + "args": { + "External id": 4732117,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755189.502, "dur": 0.051, + "args": { + "External id": 4732118,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755190.457, "dur": 0.068, + "args": { + "External id": 4732119,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755190.771, "dur": 0.050, + "args": { + "External id": 4732120,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1712360755191.616, "dur": 0.058, + "args": { + "External id": 4732121,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 1336753, "tid": 1336753, + "ts": 1712360755841.291, "dur": 3796.414, + "args": { + "External id": 4732122,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "2.0220929916117064e-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": 11633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 1336753, "tid": 1336753, + "ts": 1712360759094.773, "dur": 337.579, + "args": { + "External id": 4732123,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "2.0220929916117064e-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": 11634 + } + }, + { + "name": "process_name", "ph": "M", "ts": 1712358640923.781, "pid": 1336753, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 1712358640923.781, "pid": 1336753, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1712358640923.781, "pid": 1336753, "tid": 0, + "args": { + "sort_index": 1336753 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1712358640923.781, "pid": 1336753, "tid": 1381210, + "args": { + "name": "thread 1381210 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1712358640923.781, "pid": 1336753, "tid": 1381210, + "args": { + "sort_index": 1381210 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1712358640923.781, "pid": 1336753, "tid": 1336753, + "args": { + "name": "thread 1336753 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1712358640923.781, "pid": 1336753, "tid": 1336753, + "args": { + "sort_index": 1336753 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1712358640923.781, "pid": 1336753, "tid": 1381210, + "args": { + "name": "thread 1381210 (pt_autograd_0)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1712358640923.781, "pid": 1336753, "tid": 1381210, + "args": { + "sort_index": 1381210 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 1712358640851.343, "dur": 2120523.070, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1712358640851.343, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 1712358640851.343 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 1712360838035.453 + } + ], + "traceName": "exp/mtp.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine/profile_trace/iteration_195584/rank0_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file